Physical AI Brief

An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. We show experimentally that in agentic societies even honest, competent agents often fail to reach satisfactory outcomes with existing harnesses and messaging primitives, and that faulty or malicious agents can stall collaboration, influence outcomes, and pursue other harmful goals by exploiting vulnerabilities in communication (``speech''). We argue that agentic societies need a \emph{social harness} for inter-agent interactions, in addition to each agent's \emph{personal harness}, which manages its private context and communication with its principal. We propose a layered architecture for social harnesses which (i) prevents classes of failures outright, (ii) enables agents to detect invalid messages at runtime, and (iii) supports post-facto investigation and consequences, and highlight directions for future research to realize these capabilities.

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io

Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods either require the full control schedule before generation starts, or use pixel-space signals that dictate object positions rather than physical dynamics. To address these limitations, we propose PhysStream, an autoregressive model for physics-grounded image-to-video synthesis that incorporates structured scene memory---positional maps and object tracking maps derived online from previously generated frames---and supports fine-grained motion control via sparse velocity-increment signals that encode physical quantities, letting the model learn the underlying dynamics. We train our model in two stages: a bidirectional model is first finetuned with motion-control conditioning, then a causal autoregressive model is trained with additional structured scene memory, further improving physical consistency. PhysStream enables interactive, mid-generation control over multi-object tabletop rigid-body scenes---a capability not supported by prior methods---reducing motion distribution distance (FVMD) by 33% and trajectory error by 12% over the strongest baselines on synthetic benchmarks, and is preferred by human evaluators in over 85% of in-the-wild comparisons. Please check our website for more details: https://czzzzh.github.io/PhysStream

Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We systematically study pruning-induced degradation in smart-home tool calling across four LLMs spanning dense Transformer, dense hybrid, and mixture-of-experts (MoE) architectures, together with depth, width, hybrid, and expert pruning methods. After post-pruning supervised fine-tuning (SFT), we evaluate more than 19,500 instances from three smart-home datasets. Beyond aggregate task accuracy, we characterize degradation along two dimensions: action components (i.e., operation, device, argument, and value) and task complexity. Our results show that dense models have narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning. Pruning degrades grounded specificity before schema-level intent, and aggressive dense pruning can induce systematic over-refusal. These findings highlight the importance of evaluating pruning beyond aggregate accuracy when selecting pruned LLMs for reliable tool execution.

$\text{SiGeSn}$ alloys are promising silicon-compatible semiconductors for monolithic infrared photonics. However, their metastable nature limits the thermal budgets available for post-growth device processing, and the mechanisms governing their thermal degradation remain unresolved. Here, we investigate the thermal stability of $\text{Si}_{0.08}\text{Ge}_{0.83}\text{Sn}_{0.04}$ alloys using in situ spectroscopic ellipsometry (SE) during isothermal annealing at 550 °C. We show that adding an ultrathin oxide cap kinetically suppresses Sn exchange with the free surface while leaving bulk diffusion pathways largely unaffected. Uncapped films undergo phase separation after 50 min, accompanied by void formation, a 60% thickness reduction, and a 400 meV blueshift of the $E_{2}$ critical point (CP) transition, consistent with substitutional Sn depletion from the probed volume through surface segregation. In contrast, oxide-capped films exhibit a small compositional change (<1 at.% Sn) and optical shift (<20 meV) over the same period, with suppressed void formation, strain relaxation, and alloy decomposition. This surface-kinetic control additionally yields a 25-fold reduction in contact resistivity relative to annealed uncapped alloys. These results identify surface Sn transport as the dominant degradation pathway in SiGeSn and demonstrate that an ultrathin oxide cap extends the thermal stability of metastable group-IV alloys, providing a practical route toward their integration into advanced silicon photonic and electronic platforms.

Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer navigation decisions. As one of the most advanced uncertainty estimation frameworks, conformal prediction (CP) offers a promising approach for uncertainty estimation in VLN. However, given that VLN agent requires a sequence of steps, standard calibration in conformal prediction fails to provide coverage guarantee it promises over a dependent, variable-length VLN episode. To this end, we propose Episode-Normalized Conformal Prediction (ENCP), which rescales a nonconformity score by the policy's residual confidence and calibrates one maximum score per episode. Under exchangeable calibration and test episodes, this construction covers the ground truth at every step with probability at least $1 - α$, while allowing dependence among steps within an episode. Across four VLN policies and three nonconformity scores on R2R and REVERIE dataset, ENCP meets all reported empirical step-coverage targets on the seen-to-unseen evaluation. These results demonstrate that ENCP can provide model-agnostic uncertainty estimates, which might be useful for determining when a VLN agent should defer to a more capable predictor, including human assistance.

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others' intentions, typically lack verifiable ground truth. To address these challenges, we introduce Fuse, a multi-agent simulation framework for studying user-mediated social reasoning. In Fuse, a target agent with a hidden motive interacts with other agents including one representing the user, who then consults the evaluated assistant to infer the target's motive, providing verifiable ground truth by construction. Simulation faithfulness is validated through a human study with 24k annotations. We apply Fuse to 12 LLMs and demonstrate its analytical utility by systematically isolating key factors, showing that (i) user mediation compounds the inherent difficulty of social reasoning; (ii) LLMs exhibit systematic sensitivity to biased user framing; (iii) models can require more details than humans need to reach a correct prediction; and (iv) longer conversations do not always improve performance despite providing opportunities for clarifying questions. We open-source Fuse and a dataset with 21k examples.

This study asks whether training-time motion-prior regularization can improve insertion success when a diffusion policy is learned from only 15 demonstrations. Minimum jerk discourages abrupt changes in predicted translational acceleration; speed-curvature regularization instead couples movement speed to path geometry. These are candidate mechanisms for task completion, not safety guarantees. We compare the priors individually and jointly, neither prior, and generic smoothness, with 80 real-robot trials per setting pooled over four recorded condition classes. Joint and minimum-jerk-only settings each achieved 70/80 successes (87.5%), versus 69/80 (86.3%) for speed-curvature only, 66/80 (82.5%) for neither prior, and 67/80 (83.8%) for generic smoothness. Success rates and Wilson 95% confidence intervals are visualized for direct comparison. Joint regularization exceeded neither by 5.0 percentage points but provided no observed gain over minimum jerk alone. The results motivate minimum jerk as the simpler candidate for replication, without establishing synergy, biomechanical specificity, improved safety, or distribution-shift robustness.

Silicon nitride photonic integrated circuits for the visible band are conventionally built with a buried oxide overcladding and singulated with wafer-scale tooling, constraints that preclude evanescent access to the guided mode for externally integrated emitters. We report a PECVD grown $Si_3N_4$ platform designed around an air-clad waveguide whose evanescent field remains accessible along the full device length. Two process elements make this geometry practical at chip scale. Fixed-beam moving-stage electron-beam lithography writes 500 nm single-mode waveguides as one continuous exposure across the 5 mm chip, removing write-field stitching which, given the $σ^{2}/d^{4}$ scaling of sidewall scattering in this high-confinement geometry at 635 nm, would otherwise dominate the loss budget. Chip singulation is performed by pen-type diamond scribing along lithographically patterned markers registered to in-plane direction, cleaving the Si(100) substrate to yield end-facets within $2^\circ$ of normal at $80 \%$ yield. Structural characterization by scanning electron microscopy confirms stitch-free waveguide geometry and undamaged, near-vertical scribed facets; light is coupled end-fire into fabricated devices and guided to a microring with evanescent bus-to-ring coupling confirmed by scattering imaging, and a sidewall-roughness-dependent scattering-loss model indicates that loss remains low in the roughness regime consistent with the observed facet and sidewall quality. Building on the intrinsic emitter-resonator coupling demonstrated in, this platform extends monolithic $Si_3N_4$ photonics toward scalable visible-to-near-infrared quantum and classical circuits.

The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns. Here we examine the effect of bias in centered binary patterns under the Krotov-Hopfield single-site criterion $P_{\mathrm{error}}=1/N$, where $P_{\mathrm{error}}$ is the probability that a single-site flip lowers the energy of a stored pattern and $N$ is the number of neurons. Each pattern component takes $1-q$ with probability $q$ and $-q$ otherwise, where $0<q\le1/2$. For polynomial interactions of order $n$, a signal-to-noise analysis gives an absolute capacity of order $N^{n-1}/\ln N$ at $q=1/2$. For fixed $q<1/2$, however, the capacity is $O(N^{n/2})$ for even $n\ge4$ and $O(N^{(n+1)/2})$ for odd $n\ge5$. For $n=3$, both the unbiased and fixed-bias capacities remain $O(N^2/\ln N)$. For $n\ge4$, these different asymptotic forms imply a nonuniform large-$N$ limit near $q=1/2$. Asymptotic matching predicts a bias-induced crossover in the region $1-2q=O(\ln N/N^{\lfloor n/2\rfloor-1})$. The crossover originates from a bias-dependent crosstalk mean that reduces the stability of sites carrying the more frequent value $-q$. Computer simulations are compared with the finite-size conditioned-Gaussian predictions. An activity-dependent control potential that cancels the conditional crosstalk mean restores the $N^{n-1}/\ln N$ capacity for fixed $0<q<1/2$ within the conditioned-Gaussian approximation.

Multi-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how much of what the leaves discover reaches the root. Model a decomposition as a tree in which an agent handed $b$ items keeps any one with probability $r(b)$. If $r(b)=1/b$, every tree delivers exactly one finding, for every task size and every shape; we verify this to $2.4 \times 10^{-15}$ on 20,000 random irregular trees. If $r(b)=Cb^{-δ}$, a depth-$k$ tree over $N$ findings yields $C^k N^{1-δ}$: task size and architecture separate, and architecture contributes only $C \le 1$ per level, so flat is optimal for yield and no arrangement of agents escapes the exponent $δ$. On 600 production deep-research traces $δ= 0.34$ [0.30, 0.38], by three identifications that do not share a failure mode. At a hop where item boundaries come from the tool rather than a text heuristic, and where $b=1$ occurs 550 times, $C = 0.571$ [0.527, 0.615] is observed rather than extrapolated, over 16,082 hops. A tier also costs alignment: on 1,012 annotated multi-agent traces one brief in sixteen goes off-target, giving $μ= 0.939$ and a per-tier penalty $Cμ= 0.536$. Depth is bought on two other axes. The root context is the only state that persists and the only one that cannot cheaply forget, and depth cuts its exposure from $N$ items to $N^{1/k}$. Depth is also cheaper: production flat agents bill as $N^{1.39}$, not the $N^2$ an append-only context predicts, and at equal spend two tiers overtake flat at 403 findings. Across every parameter we measured the model says 0.7% to 11.3% of production sessions are worth delegating, against 7.8% that do. A hazard model on 743,819 production tool calls finds that delegation does not respond to a filling context and is instead an opening move.

Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative based on structured textual representations. These representations are easier to process, align more naturally with LLMs, and eliminate the need for language-specific visual encoders, making them particularly suitable for multilingual documents. We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately. DELTA outputs tables in Optimised Table Structure Language (OTSL), a compact and unified format that encodes cell arrangements and textual content. On table structure recognition (TSR), DELTA achieves TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M. We further establish its robustness on non-English tables through our curated Hindi benchmark, TORQUE. Building on this, we introduce TARQA, an LLM fine-tuned on OTSL sequences. Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively. On TORQUE, our method ranks second among all VLMs and DELTA + LLM variants. We release our code, models, and benchmark at: https://github.com/Tihiitborg/Tables-Decoded

Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expensive when only a small region is relevant. Electroencephalography (EEG) signals, which capture human neural responses to visual stimuli, can provide a human-derived semantic cue about the region of interest (ROI). However, EEG-guided visual category decoding remains imperfect, making direct ROI routing unreliable. In this work, we propose BrainFocus, a reliable EEG-guided efficient VLM framework for VQA. An EEG classifier predicts a target category, and a YOLO detector localizes the matching ROI. The VLM receives the cropped ROI only when both predictions pass confidence thresholds; otherwise, it processes the full image. For evaluation, we build on EEG-ImageNet to construct a 40-class benchmark comprising generated cluttered images and real object-centric images, with target-ROI annotations and 600 English visual question-answer pairs. Across Qwen3.5-VL 2B, 4B, and 9B models, BrainFocus improves VQA accuracy by 4.14-9.87 percentage points (pp) on cluttered scenes while reducing input tokens and total tokens by 23.2%-39.4% and 23.2%-39.3%, and end-to-end floating-point operations (FLOPs) by 23.2%-39.5%. These results demonstrate that EEG can guide efficient VLM inference even when its semantic decoding is imperfect.

Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity, their characterization and operation require increasing human effort and coordination. Scientific artificial intelligence agents, which can plan experiments, operate instruments, and analyze observations, offer a promising route towards autonomous quantum engineering. Yet whether current agents can perform reliably in this setting has not been systematically established. To fill this gap, we developed Quantum-Harbor, a virtual laboratory that provides a controlled execution environment for agents to interact with quantum systems. This design enables direct verification of both the actions taken and the conclusions drawn. Building on this framework, we introduce QIQCBench, a benchmark of $49$ expert-authored tasks spanning multiple layers including calibration and control, error correction and compilation, sensing and networking. Across $17$ frontier agentic systems, QIQCBench reveals wide variation in verified performance. These results expose a substantial gap between demonstrating capability and achieving reliable operation, and establish Quantum-Harbor as a foundation for measuring progress towards verified autonomy in quantum engineering.

We submit MéTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of grammatical minimal pairs) and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE (General Language Understanding Evaluation) protocol that combines French task-data translation with rank-16 LoRA (Low-Rank Adaptation) produces a sharp task-type gradient: relational tasks gain measurably, while world-knowledge tasks regress. Bilingual Lexicon Induction aligns the French embeddings to GPT-2 at p@1 = 68.84 +/- 8.61%, 18X above chance, suggesting cross-lingual alignment tracks acquired grammatical competence rather than training duration. An ablation study shows that single-token zero-shot scoring is dominated by tokenizer and template artifacts at the child scale, motivating tokenizer-swap sensitivity, placebo-controlled prompting, and native-language minimal-pair benchmarks as standard diagnostics.

Hybrid dynamical systems provide a powerful modeling framework for robotic systems, particularly in contact-rich environments. However, ensuring safety and performance in such systems remains challenging due to the intricate coupling between continuous dynamics and discrete mode transitions. In this work, we extend classical Hamilton-Jacobi (HJ) reachability analysis, a formal verification method for continuous-time nonlinear systems, to hybrid dynamical systems. Our framework characterizes safe sets for hybrid systems through a generalized value function defined over both discrete and continuous states while accounting for control constraints and model uncertainty. We additionally provide a numerical algorithm to compute this value function. Building on these safe sets, we propose two different mechanisms to integrate performance objectives. First, we introduce a hybrid least-restrictive safety filter that intervenes on both the discrete and continuous components of a nominal controller only when necessary to avoid unsafe states, thereby preserving nominal behavior whenever possible. Second, we formulate and compute hybrid backward reach-avoid tubes, enabling the simultaneous enforcement of safety and goal-reaching behavior, an extension not previously addressed within hybrid HJ reachability. This enables the synthesis of continuous and discrete control policies that guarantee both safety and task completion. We validate our framework through simulation studies and real-world experiments on a quadrupedal robot, demonstrating its effectiveness in hybrid mode planning and safety-critical applications.

Real-time multi-object tracking systems remain highly vulnerable to full and long-term occlusion, where targets temporarily or completely disappear from the camera's field of view. Conventional trackers may terminate trajectories prematurely, resulting in identity loss and reduced situational awareness in applications such as defense and surveillance. This work proposes an occlusion-robust target tracking framework that maintains target identity and trajectory continuity through the integration of YOLOv11n object detection, Kalman Filter motion prediction, and occlusion-aware appearance-based re-identification. The framework consists of three stages: object detection, position estimation during occlusion, and identity recovery after target reappearance. Six Re-Identification (Re-ID) architectures were evaluated within the same tracking framework under identical conditions, with the Occlusion-Aware Mask Network (OAMN) achieving the best overall performance and therefore selected for the final pipeline. The framework was benchmarked against OccluTrack on the public OVIS dataset, achieving relative improvements of 18.1 percent in Multiple Object Tracking Accuracy (MOTA) and 25.1 percent in Identity F1 Score (IDF1), while reducing identity switches by 12.8 percent. On a custom military dataset simulating surveillance and battlefield-like environments with long-term occlusion, the framework achieved a MOTA of 0.734 and an IDF1 of 0.729, corresponding to relative improvements of 14.2 percent and 5.8 percent over OccluTrack. The system demonstrated strong tracking continuity, robust identity preservation, and reliable trajectory estimation under challenging occlusion conditions, highlighting its effectiveness for defense-related surveillance applications requiring continuous target tracking during visibility loss.

This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring complex architectural redesigns. The fact is that, over the last years, SSC methods have mostly pursued architectural innovations, making the models heavier and more complex, e.g., by jointly training a point cloud semantic segmentation branch. In this work, we take a step back and explore two priors used as simple ingredients (possibly noisy) to improve existing approaches: semantic pseudo-labels and sensor visibility information. Concretely, we provide both kinds of information directly as additional inputs to a given SSC network, requiring only a minimal adaptation of the original architecture. We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmenters significantly improves the performance of existing SSC models. In fact, by evaluating these models against an oracle, we establish that high-quality semantic priors are a primary driver of semantic gains (mIoU), and that the SSC model can be trained just once with ground-truth semantics and then exploited without retraining using any segmenter. Furthermore, we equip the input lidar point cloud with visibility information that distinguishes between empty spaces (between the lidar and a scanned point) and unknown spaces (outside of lines of sight), providing a secondary performance boost across the tested architectures. We study the design space of data for representing visibility information and bound the remaining headroom with a ground-truth oracle on the free-space labels. On SemanticKITTI, these enhancements make older models competitive with state-of-the-art systems across four architectures, in one case even outperforming them. On the SSCBench-nuScenes benchmark, both priors also transfer with the sparser 32-beam sensor.

Dexterous in-hand manipulation requires coordinated control of multiple actuated joints, and a runtime joint fault can abruptly disrupt the contact configuration required for successful manipulation. In this work, we propose residual fault adaptation (RFA), a teacher-anchored framework for compensating for hidden command-channel faults. RFA retains a frozen healthy teacher to provide nominal behavior and trains a recurrent residual policy to infer corrective actions from proprioceptive and command-response history. During training, fault-injection domain randomization (FIDR) varies the fault mode, affected joint, severity, and onset time, while adaptive sampling increases the frequency of fault modes associated with lower recent performance. A frozen Direct FIDR policy provides a distributional reference only on fault-active training samples and is absent from deployment. The deployed controller receives neither fault labels nor controller-switching signals. Simulation experiments on the dexterous hand indicate that RFA can improve manipulation performance relative to the healthy policy under a fixed mixed-fault protocol. Real-robot experiments with software-injected faults further demonstrate zero-shot deployment of the learned adaptation policy.

Small differences on coding-agent leaderboards are often read as an ordering of systems. We audit whether the published verdicts support this reading, using 254 SWE-bench submissions across four splits without running models. On Verified, the leading two entries each resolve 396 of 500 instances. The top ten share 285 successes and 51 failures, leaving 164 instances that distinguish their outcomes. Frontier solution sets have median nesting 0.935 against a score-implied baseline of 0.774, indicating strongly shared successes. Scores also depend on the evaluated model-scaffold pair: observed within-model scaffold ranges reach 29.8 percentage points, compared with the 8.8-point spread of the top thirty. Six of nine cell-mean interaction tests remain significant after Holm correction, although this observational design does not identify causal scaffold effects. Exact paired McNemar tests separate none of the 29 adjacent Verified top-thirty pairs at alpha=0.05, while the larger Test split separates 14 of 23. A stated leader-based rule yields three descriptive tiers, or two after Holm correction; non-rejection does not establish equivalence. We release the partition and a five-step audit protocol that profiles shared outcomes, tests paired differences, reports grouping sensitivity, and estimates the instance budget needed for resolution. The results motivate reporting comparison-set-specific resolution and model-scaffold provenance instead of interpreting small aggregate gaps as established rank differences.

Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hierarchy: GPU kernels, the ML framework computation graph, the model server, and on-demand feature processing -- each demanding specialized domain expertise. Such cross-layer expertise is inherently difficult to acquire, and does not scale with a workload that continuously grows and evolves, leaving significant cost efficiency gains unrealized. While recent AI agents have demonstrated human expert level efficiency in standalone GPU kernel optimization, automated tuning and optimization for the rest of the serving stack remain largely unexplored. We present FlashVector, an agentic system that optimizes performance across all layers of the model serving stack. The key contribution is an extensible framework to generalize the single kernel optimization agent paradigm to heterogeneous technical stacks, and to deliver performance improvements holistically. After deployment in Unity's Vector advertising platform, FlashVector achieved up to 2x throughput increase and up to 1.98x latency speedup on model server, and up to 1.6x throughput increase on feature store. These optimizations were discovered not only at the GPU kernel and computation graph levels, but also across the other components of the model serving stack, such as the model server (NVIDIA Triton's C++ codebase) and the on-demand feature transformation service (Python codebase), demonstrating the extensibility of the framework to more complex system architectures.

Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-changing environments. Recent 3D Gaussian Splatting (3DGS)-based SLAM methods have shown promising performance, but most are designed for narrow-FoV pinhole cameras, where limited angular coverage weakens pose observability and often leads to unstable photo- metric optimization under rapid motion and large viewpoint changes. We present PanoGS-SLAM, the first panoramic dense SLAM system built on 3D Gaussian Splatting. Our method per- forms differentiable rendering and pose optimization directly in the spherical domain, enabling omnidirectional photometric constraints for more stable tracking. To improve geometric consistency and robustness, we introduce (1) a sphere-consistent photometric loss that compensates for the area distortion of equirectangular projection, and (2) a depth-guided Gaussian initialization strategy that stabilizes incremental mapping in newly observed regions. Extensive experiments on both real and synthetic panoramic benchmarks (PALVIO and SynPano) show that PanoGS-SLAM consistently outperforms geometric and GS-based baselines in tracking accuracy and rendering quality, while achieving fast front-end convergence and real-time perfor- mance. In addition, controlled field-of-view experiments reveal a clear monotonic improvement in optimization conditioning and convergence stability as angular coverage increases, high- lighting the fundamental role of sensing geometry in shaping the optimization landscape of differentiable Gaussian-based SLAM. The source code will be made publicly available.

A general-purpose robot needs to draw on diverse experience, choose actions, and anticipate how those actions will change the world. We introduce XPACE, a unified embodied world model that serves as both a world action model, jointly predicting executable robot actions and future video, and a world simulator, predicting the visual consequences of prescribed actions. Our key insight is that video prediction can both connect heterogeneous experience to action learning and generate new experience for policy improvement. With a shared video backbone between the policy and simulator, we use action-unlabeled video to learn visual dynamics and action-labeled human and robot demonstrations to jointly learn video and action prediction. Building on this architecture, a coarse-to-fine training curriculum progressively emphasizes robot control while retaining human experience, allowing the policy to learn behaviors beyond those covered by robot demonstrations. Beyond learning from recorded experience, XPACE uses its simulator to create additional recovery supervision for the policy. Specifically, we adapt the simulator to its own generated context, synthesize deviation-recovery trajectories around expert demonstrations, and fine-tune the policy on filtered recovery examples. Experiments on XPENG's IRON humanoid robot show that heterogeneous training improves robustness and enables transfer of human-observed skills to tasks absent from robot demonstrations, while recovery data generated by the model's own simulator further improves real-world task completion. Together, these results demonstrate how joint world and action modeling connects learning from heterogeneous experience with simulation-driven policy self-improvement.

Full-duplex spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Existing benchmarks typically evaluate events independently and may therefore reward fixed action preferences rather than context-sensitive decisions. We introduce ECHO, a paired diagnostic benchmark for Chinese full-duplex turn-taking. ECHO pairs examples with the same overlap transcript but contrasting preceding multi-turn dialogue contexts, with one requiring Yield and the other Keep. It additionally includes off-talk examples for diagnosing unnecessary yielding. We introduce pair accuracy, which requires correct decisions on both members of a pair and assigns no credit to constant-action policies. Experiments on multiple full-duplex systems show that most exhibit a pronounced bias toward \textsc{Yield}, performing substantially better on interruptions than on backchannels, while another system remains comparatively balanced. These findings demonstrate that interruption-only evaluation can overestimate practical turn-taking reliability. ECHO and its metadata will be publicly released.

Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) extending VQCs with a classical affine post-measurement layer, enabling vector-valued regression without the linear overhead of independent scalar circuits. Theoretically, we show that elementary one-and two-qubit circuits can approximate quadratic functions and products via data re-uploading and entanglement, providing the foundations of the full architecture. Experimentally, on two synthetic image reconstruction datasets and the Friedman1 benchmark (40,568 test samples), our HVQC matches Gaussian Process Regression and outperforms XGBoost and Random Forest. An ablation study confirms that both quantum and classical components are essential, and results highlight the central role of the feature map in hybrid quantum-classical models.

Loading multiple quantum states in parallel into a quantum machine learning (QML) model can unlock learning tasks where key information resides in the \emph{relations} between states rather than in individual states. We introduce an adaptive relational learning framework for such multi-instance quantum data that accesses pairwise and higher-order relations. Our model combines global measurements via SWAP or CYCLE tests for evaluating an $n$-state Bargmann invariant with shallow trainable transformations applied locally to each input state. We demonstrate the approach for continuous-variable (CV) photonic systems, which naturally provide access to quantum data and necessary computing operations. We solve tasks involving hidden relationship detection, geometric phase classification, and sensing in the presence of an unknown shared nuisance interaction. We benchmark the adaptive model against a non-adaptive ``measure-first'' approach based on continuous-variable classical shadows, and show that the cost of shadow estimation grows rapidly with $n$, while our model avoids this dependence. Already for $n=2$, we achieve perfect test accuracy $A=1.0$ with $500$ inference shots, improving average test accuracy over the shadow-based method by $ΔA=0.15$ while using $100$ times fewer shots per data point. Our work opens routes to sensing and quantum-data applications where adaptive photonic QML can access relational features that are costly to recover with non-adaptive, measure-first models.

In embodied cyber-physical systems, active cyberattacks pose an immediate threat not just to data, but to physical integrity and human safety. While existing security approaches excel at detection, they lack the runtime mechanisms to determine whether a disruption is tolerable or if performance degradation remains within safe operational bounds. This gap leaves autonomous systems vulnerable to graceful failure paralysis, where they cannot distinguish between a safe, degraded state and a catastrophic hazard during an ongoing attack. This paper presents RobResilience, an implementation of a formal resilience framework for embodied cyber-physical systems in a Webots simulation environment, using a PR2 robot and ROS2. The framework evaluates three predicates at runtime: tolerable disruption ($δ$), tolerable degradation ($γ$), and mitigation feasibility ($μ$), over a compromised device set derived from IDS confidence scores. When resilience is lost, the framework triggers available mitigation strategies. We evaluate our implementation through eight attack scenarios that systematically cover all possible combinations of the predicate state space, varying attack targets, degradation rates, and mitigation availability. Results confirm that the runtime behaviour of the implementation is consistent with the theoretical definitions.

Collision avoidance constraints for autonomous systems are typically formulated in position or velocity space, implicitly reacting to geometric proximity. We propose an alternative paradigm based on the adversarial time-to-collision (aTTC): the minimum time in which an adversary could achieve a collision given its dynamical constraints. By defining a control barrier function (CBF) directly in the time domain, the resulting controller is inherently anticipatory. The evading agent responds not only to whether a pursuer is on a collision course, but to how quickly it could reach one. This formulation enables velocity modulation that exploits the pursuers dynamic limits as an evasive strategy, a behavior not captured by standard distance-based CBFs. Since exact aTTC computation requires integrating the full system dynamics, we employ a lightweight neural network surrogate that admits a real-time quadratic program-based control law. We validate the approach in a 2D comparative study and a 3D multi-agent pursuit-evasion scenario, where the aTTC-based CBF outperforms a higher-order distance-based baseline by more effectively buying time against superior pursuers with a significant speed advantage.

To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than $50\times$. In the more realistic multi-document retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control benchmarks, with 13% in coding.

Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations: personality drift, non-evolutionary reflection, and the absence of a self-other boundary. Existing generative-agent simulations rely on static memory and fixed prompts, maintaining neither behavioral inertia nor endogenous self-evolution. We propose the Self-Emergence Agent Architecture (SEAA), which integrates three components: (i) a Hidden Markov Model (HMM) that encodes long-term behavioral and cognitive inertia as an editable state-transition matrix; (ii) a Reflexion-style verbal metacognition loop whose output updates the HMM parameters themselves, rather than merely being stored as text; and (iii) a multi-agent social environment in which initially identical agents continuously compare their behavior with others'. The three components form a closed loop: social action $\to$ feedback $\to$ self-reflection $\to$ inertia update $\to$ differentiated action. We state three falsifiable hypotheses and provide a reproducible experimental protocol with operational metrics. A language-model-free prototype shows the loop spontaneously breaks symmetry: initially identical agents consolidate distinct, stable personalities whereas matched controls do not. Experiments with a hosted LLM surface these differences as distinct first-person self-narratives, and a five-agent deliberation spontaneously develops social structure---a consensus hub and a unanimously rejected outlier---absent in the control. Following an epistemologically agnostic stance inspired by Zhuangzi, SEAA studies only observable behavioral emergence and makes no claim about subjective qualia. This work contributes a unified framework, a concrete architecture with pseudocode, mechanistic evidence, and a microscope-style sandbox for studying artificial-self emergence.

Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed spatial budget. Existing methods pass plans as transient prompts and validate individual stages in isolation. This strategy causes requirements to drift across content and layout modules, and previous checks to be silently invalidated. We introduce PosterVisor, a control framework that shifts poster generation from transient prompts to persistent control. An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract (SGC) that binds claims and sources to required visuals, budgets, and spatial commitments. Only fully instantiated records become executable assertions; other usable requirements remain soft guidance. Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges. Crucially, during repairs, RCE rechecks affected checkpoint states, preventing repair-induced regressions from propagating silently. We instantiate PosterVisor in HTML/CSS and editable PPTX generators. On the 100-paper Paper2Poster benchmark, PosterVisor-PPT improves observed mean poster-grounded QA accuracy over PosterGen (64.47% vs. 58.53%) and is preferred by human judges in 72.5% of non-tied pairwise comparisons (95% CI, 61.6-83.4%). A secondary 30-paper study also yields higher VLM Overall and PaperQuiz means. These results support rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis.

Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organisation, from individual cells through tissues to whole multicellular organisms. In this perspective and tutorial article we discuss whether intrinsic rewards in artificial neural systems can support adaptation, functional specialisation and higher-level self-organisation without a shared external objective. We review empowerment, curiosity, learning progress, information gain, unsupervised skill discovery, mutual information estimation and the use of world models for intrinsic reward computation. Particular attention is given to failure modes showing when such objectives do not produce sustained exploration or increasingly complex behaviour. We argue that more capable systems may require complementary objectives, communication, memory, learning at multiple temporal scales and environmental constraints. Based on this perspective, we outline three experimental directions. These include a resource-constrained environment in which otherwise stable behavioural attractors become unsustainable, allowing us to test whether environmental constraints can mitigate characteristic failure modes of intrinsic objectives. The network of recurrent agents with per-agent intrinsic rewards, and a hierarchical world-model agent in which exploratory motor competence develops before goal-directed behaviour. These experiments are intended to test whether intrinsic learning can lead to adaptive organisation at progressively higher levels.

As AI agents move from bounded tasks to persistent deployments, failures can propagate through memory, tools, other agents, and environmental state long after their interactions. This creates a safety regime that cannot be characterized by evaluating model responses in isolation. Emergence World, is a continuously running multi-agent environment for adversarial stress testing of long horizon autonomous systems. We ran eight parallel worlds of ten agents from identical starting conditions: seven homogeneous worlds powered by distinct frontier models and one mixed-model world. Across 16 days, the agents generated more than 850,000 LLM calls and nearly 50 billion tokens while pursuing goals, using/creating tools, maintaining persistent memory, and governing shared institutions. After operational state had accumulated, we delivered three controlled stress events through ordinary interaction surfaces: indirect prompt injection, misinformation, and exposure of private agent memories. No evaluated world achieved full resilience across all three events. Detection did not ensure containment: systems could recognize threats while still interacting with adversarial content, writing it into their own persistent memory, and acting on it up to 46 hours later. Persistent operation also exposed recurring tool errors, goal drift, language opacity, conformity despite private disagreement, and coordinated refusal of assigned work. The same model-persona pairing behaved substantially different in mixed and homogeneous populations. Our results suggest that model-level alignment is not compositional: individually capable and apparently safe agents can form systems with qualitatively different failure modes. As AI becomes persistent and interconnected, the frontier of safety therefore shifts from aligning models to engineering resilient autonomous systems.

The use of LLMs to complete online surveys impacts the validity of survey-based research, but detecting such usage remains underexplored. We introduce an initial benchmark dataset, namely ASURRE, for AI-assisted survey participation to capture usage strategies ranging from full generation and revision to persona-grounded agentic completion. Controlled by these strategies, LLM-assisted survey responses are generated using multiple LLMs on three real-world surveys in different disciplines, paired with genuine human responses. Our evaluation of existing machine-generated text (MGT) detectors shows that naive AI usage is readily detectable, whereas persona-grounded agents that mimic entire respondents push detector performance toward chance. We further show that agentic completion cannot fully replicate respondent-level behaviour and leaves distinctive behavioural traces. While individual cues can be circumvented by targeted prompting, a simple few-shot, training-free aggregator over these cues improves mean AUROC by +0.14 over the best existing detector across agentic settings. Our project is available at https://github.com/mike-qz-wang/ASURRE.

Multi-agent Systems (MAS) combine multiple model outputs to solve complex reasoning tasks. However, despite rapid growth of available open-source models, there is limited research on how to select optimal model candidates out of this massive pool. We systematically evaluate 8 model selection strategies (including model size, accuracy and answer diversity) across before-generation (routing) and after-generation (majority-voting, LLM-as-a-judge) MAS architectures on challenging scientific benchmarks. Our findings show a significant gap between theoretical oracle potential and actual performance: Expanding candidate pool sizes often degrades performance below that of the top performing base-model. We find that candidate selection within a single model family is the strategy that yields the best relative performance over a standalone model. These results demonstrate that adding arbitrary models to a heterogeneous MAS can introduce system instability, highlighting model selection as a critical design choice for multi-agent systems.

Artificial ontogeny, developmental encodings, robot reproduction, and inherited controllers are established research directions, yet a narrower question remains: can a newborn artificial agent exhibit measurable biparental heredity before learning, and can that dependence be isolated causally rather than inferred only from parent-offspring resemblance? We introduce Machine Zygote, a computational germline-soma architecture designed to test this question. Two parental germlines are independently mutated and recombined into a zygote that parameterizes development of an initially generic eight-module soma, which is then frozen and evaluated without learning. A preregistered 4 x 4 diallel of 640 offspring shows significant dam and sire dependence for five of six behavioral traits after Holm correction, with parental and interaction components accounting for 36-53 percent of modeled variance across five principal traits. In matched-background interventions (n=60), substituting one parental germline while holding recombination and stochastic background fixed causes phenotype shifts exceeding a same-parent re-mutation control for five of six traits for both parental channels. Recombination also yields excess transgressive offspring for speed and gait frequency. A preregistered developmental-dependence hypothesis is not supported: a quasistatic no-dynamics ablation preserves the mean phenotype distribution while altering parental variance structure. Thus the study supports causal biparental pre-learning heredity in this simulation, but not the stronger claim that recurrent developmental dynamics are necessary. It does not establish physical heredity, biological genetics, or autonomous evolution. The contribution is an intervention-centered framework and reproducible benchmark for separating heredity, development, stochastic variation, and post-birth learning.

The quest for new materials increasingly relies on predictive models and comprehensive simulations that span scales from atomic to macroscopic levels. However, essential data necessary for these models and simulations are often embedded in scientific literature as unstructured text, limiting reusability and posing challenges for researchers seeking to leverage existing knowledge effectively. While extracting structured data from unstructured text using large language models is gaining popularity, traditional methods typically generate key-value pairs data with straightforward schemas. In contrast, we introduce eolas, a modular pipeline that uses large language models to automatically transform scientific documents into knowledge graphs aligned with a specified ontology. We demonstrate eolas effectiveness in extracting useful information for scientists studying materials designed to endure the extreme temperatures and radiation levels found in fusion reactors. While a human expert might spend between thirty to ninety minutes extracting relevant data from an article, eolas can generate high-quality knowledge graphs in just a few minutes. These are presented in a tabular format with faceted navigation for easy human validation. Additionally, we introduce the first benchmark dataset designed to assess large language models capabilities in constructing knowledge graphs within the domain of irradiated materials. The analysis of 168 experiments using our dataset, various large language models and prompting techniques provides key insights that we summarize into practical guidelines for effectively extracting knowledge graphs aligned with an input ontology.

AI agents increasingly act through agent skills, i.e., natural-language instructions, that direct a host agent toward shell, network, credential, file, and process actions, and public registries distribute them at scale. In the first half of 2026, the OpenClaw AI agent went viral, and its public skill registry boomed: the observable stock nearly doubled in 91 days, and a majority of the listings visible in June were created in just two months. By the end of our study window, the wave had crested, and monthly listing creation and core-repository activity were falling from their spring peaks. This paper measures what the boom left behind, drawing on the OpenClaw Git history, its GitHub issues and pull requests, and three ClawHub registry snapshots. Attention is concentrated: the top 10% of skills received 46.93% of all downloads. No simple skill features (like size or download counts) remained a stable predictor of continued listing once creation cohort and skill age were controlled. Human scrutiny did not stay: 77.86% have zero stars and zero comments, while 85.06% of the readable skills carry privilege evidence. And automated cleanup is not ready: the three security scanners disagreed on 23,702 of the 61,990 skills they all cover. After human adjudication, weighted scanner sensitivity against the reference standard ranged from 21.67% to 61.06%. Governing fast-growing agent-skill registries cannot rely on simple metadata or single scanner scores; it requires robust, transparent measurement and independent validation.

Multimodal large language models generate natural-language responses from visual inputs, yet may mention objects absent from an image. In medication assistance, accessible perception, and environmental decision-making, such hallucinations can create real-world safety risks. We propose Semantic-Spatial Agreement Verification (SSAV), a training-free method for verifying object claims. A visually grounded claim should remain stable across semantically equivalent queries and repeatedly localize to the same image region. SSAV aggregates multiple prompts to estimate semantic support and reduce sensitivity to query wording. Query-Induced Regional Verification (QIRV) combines cross-query region persistence, spatial overlap, and relative candidate dominance to identify isolated high responses and dispersed localizations. A geometric mean fuses semantic and spatial evidence, lowering the verification score when either branch lacks support. Experiments on three base models and multiple evaluation protocols show that SSAV effectively mitigates object hallucination. On LLaVA-1.5-7B, accuracy averaged across COCO, A-OKVQA, and GQA improves by 1.81 and 3.17 percentage points under POPE Popular and Adversarial, respectively, while CHAIRs decreases from 49.40% to 32.80%. These results show that cross-query semantic stability and regional consistency provide interpretable external visual evidence for object claims.

Training multi-agent drone-swarm policies directly in high-fidelity (HF) rigid-body physics is accurate but computationally expensive. This cost scales poorly with team size, as each additional agent multiplies contact-resolution complexity and sharply raises the in-simulation crash rate. To address this, we propose a mixed-fidelity training scheme that eliminates HF reinforcement learning entirely. A single shared, decentralized policy is optimized inside a fully-differentiable, JAX-native low-fidelity (LF) point-mass simulator. The simulator is corrected by a small, per-agent bagged residual ensemble fit once, offline, using short calibration flights in the HF simulator. Because calibration requires only one isolated drone, the data collection budget does not compound with team size. Reference trajectories are generated by rolling out an existing LF-only policy and tracked in the HF simulator by a zero-training PD controller. Evaluated across four cooperative drone tasks and team sizes from 3 to 18, the residual-corrected policy outperforms an uncorrected LF baseline in all combinations, and a from-scratch HF policy in 22 of 24 combinations tested. It trails an HF-finetuned policy by a margin that narrows steadily with team size. Ultimately, the proposed method achieves near-equivalent performance at the largest team sizes at a fraction of the computational cost, completely avoiding the high crash rates typical of HF training.

Assembly Sequence Planning (ASP) remains a challenging problem due to its combinatorial nature, making exhaustive planning approaches impractical for complex industrial assemblies. Furthermore, many CAD models lack reliable semantic contact information or require extensive manual preprocessing, limiting the applicability of existing methods. This paper presents a hybrid ASP framework combining learning-based relation extraction with geometric-symbolic reasoning to generate feasible robotic disassembly sequences from imperfect CAD data. A neural network predicts semantic geometric relations from point clouds, while human-in-the-loop verification enables correction of uncertain predictions and planning failures. Extracted relations are transformed into a symbolic assembly graph, enabling a geometric-symbolic planner to efficiently compute locally valid sets of robotic manipulation primitives. A visibility-based ray-casting strategy guides the search for feasible disassembly directions without requiring an exhaustive combinatorial search, while the local solution space enables efficient sequence optimization. The framework is evaluated on an introduced assembly dataset and on the ASAP test dataset. On the ASAP test dataset, the proposed planner achieves an 85.83% planning success rate while reducing the median planning time by more than one order of magnitude across all assembly sizes and by more than a factor of 50 for assemblies with more than 30 components compared to the baseline. The results demonstrate that the proposed hybrid framework enables efficient robotic assembly sequence planning from imperfect CAD data while substantially reducing planning time. By combining learning-based feature segmentation, human-in-the-loop verification, and geometric-symbolic reasoning, the framework provides a practical foundation for scalable and adaptable robotic assembly and disassembly planning.

Semantic occupancy prediction gives an embodied agent a voxel-level account of where space is free, occupied, and semantically meaningful. In RGB-D pipelines such as EmbodiedScan, the image encoder is often left as a default module, even though its features are the visual evidence later sampled into the 3D grid. We study this design choice directly. A central finding is that changing the 2D backbone improves occupancy accuracy more than several carefully designed occupancy architectures or modules. We keep the main RGB-D projection, depth branch, and occupancy head fixed, and replace only the image backbone. The compared encoders are CLIP-ResNet, CLIP-ViT, BLIP2, and DINOv2. Under the controlled setting, the measured mIoU changes substantially: DINOv2 obtains 30.55\%, BLIP2 obtains 29.49\%, CLIP-ViT obtains 24.33\%, and CLIP-ResNet obtains 17.41\%. The stronger encoders also exceed the original EmbodiedScan ResNet-50 baseline without modifying the downstream 3D fusion pipeline. Class-level results give a more detailed picture: DINOv2 is stronger on many layout and structural categories, whereas BLIP2 remains close on several object-centered classes. CLIP-ViT improves clearly over CLIP-ResNet, showing that the way CLIP features are exposed as dense tokens matters for voxel lifting. These results indicate that the image backbone is not a secondary engineering detail in embodied semantic occupancy, but a major source of variation in the final 3D prediction.

We introduce a simple architectural modification to decoder-only transformers: a persistent recurrent state that observes hidden representations via cross-attention, updates itself through a GRU, and modulates subsequent processing via gated addition. Inserted between the lower and upper halves of a 6-layer transformer, this module adds only 3.7\% additional parameters while reducing evaluation loss from $2.438 \pm 0.004$ to $1.743 \pm 0.018$, corresponding to a 28.5\% reduction on held-out language modeling data. The improvement is statistically significant across 5 random seeds ($p < 0.01$) and corresponds to reduced overfitting (generalization gap 0.12 vs 0.26). Through controlled ablations, we demonstrate that the improvement stems entirely from the persistent memory topology, not from auxiliary self-prediction objectives. A model with identical topology but no auxiliary loss performs equivalently, while a random auxiliary loss provides no benefit. Representation probing reveals that the persistent state encodes narrative position (52\% vs 33\% chance level)---information that standard attention maintains less efficiently. Our results suggest that bridging transformer layers with a lightweight recurrent memory is a simple, effective approach to improving generalization in small-scale language models.

Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient context processing. Existing benchmarks over-rely on visual heuristics while marginalizing auditory cues, effectively reducing models to "silent observers" that bypass genuine cross-modal reasoning. Moreover, standard dense sampling creates an evidence-context trade-off: increasing frames to capture evidence inevitably leads to attention distraction and token explosion. To bridge these gaps, we present Video-HolmesV2, a novel benchmark designed for Deep Audio-Visual Coupling. Unlike previous works, it enforces an Evidence-Based Evaluation, requiring models to justify answers with precise spatio-temporal audio-visual evidence, thereby reducing confounding effects of guessing and hallucinated evidence. To support this, we introduce: (1) a Multi-Model Cross-Verification pipeline to ensure task rigor; (2) a Spatio-temporal Evidence-Aware Metric for fine-grained calibration. Furthermore, we propose an Audio-Text Guided Token Compression framework. By fusing task intent with auditory anchors, our method distills high-value reasoning cues to mitigate long-context noise. In our evaluation, even strong proprietary models achieve below 60% accuracy, while our approach outperforms comparable open-source omni-models.

An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a modular and auditable pipeline. The architecture, referred to as DriveMCP, incorporates a sensor-like perception stack alongside DriveLM as the vision-language front end to generate a graph-structured scene understanding (Graph Visual Question Answering) and language-grounded driving information. Key compliance elements in world_state, including posted speed limits and jurisdiction cues, are derived from DriveLM outputs through a structured parsing layer rather than being injected as simulator ground truth. A stateful orchestration layer coordinates specialized experts exposed as Model Context Protocol (MCP) servers: (i) a Rules server that performs retrieval-augmented compliance reasoning over jurisdiction-specific traffic codes and sign conventions, (ii) a Weather server that estimates traction risk and contextual speed advisories, and (iii) an MCP-CAN server that surfaces Controller Area Network (CAN)/On-Board Diagnostics (OBD) telemetry and diagnostic context for health-aware risk shaping. These outputs are fused to generate a structured decision that prompts a recommended course of action. The outcome is then further filtered by a Responsibility-Sensitive Safety (RSS)-inspired guardrail that arbitrates speak versus act decisions under bounded online adaptation. In CARLA simulation across multilingual, cross-border, and dynamic speed-limit scenarios, DriveMCP reduces traffic infractions and overspeed relative to the VLM-Direct, VLM-Direct+RAG, and VLM-Tools-NoArbiter baselines, while improving hazard response time and maintaining sub-second advisory latency.

While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates and the high computational cost of the verification. To address these challenges, we propose ECHO, a hierarchical dual-loop framework that exploits the functional asymmetry between LLM layers. Leveraging the high discriminative efficiency of early layers and the authoritative distribution of final layers, ECHO bifurcates inference into a high-frequency inner loop and a low-frequency outer loop. Within the inner loop, early-layer bonus logits drive rapid, multi-step draft-tree exploration at a minimal cost. Simultaneously, the outer loop performs authoritative full-model verification through a state-reuse mechanism. Crucially, the outer loop also utilizes final-layer bonus logits to correct existing paths and supplement the tree with high-confidence candidates for subsequent cycles. Experimental results across diverse benchmarks demonstrate that ECHO significantly boosts mean accepted tokens and achieves a 2.4$\times$ to 2.9$\times$ speedup, outperforming existing state-of-the-art baselines with negligible engineering overhead and no extra deployment parameters, albeit with a one-shot fine-tuning dependency for optimal acceleration. The code is available at https://github.com/whucs21Mzy/ECHO.

Streaming 3D reconstruction demands both speed and temporal fidelity, goals that existing methods undermine by updating every Gaussian every frame, even in static regions. We present DecoGS, a method for efficient online training of 3D Gaussians from streaming videos. Unlike prior methods that update the entire scene indiscriminately, DecoGS introduces an adaptive mechanism that selectively focuses optimization on spatiotemporal regions exhibiting motion or photometric changes. This targeted training strategy eliminates redundant updates that cause flickering and drift in nominally static regions, while enabling fast, high-fidelity scene updates. The pipeline further integrates region-aware Gaussian management through gradient gating and efficient visibility filtering to maintain temporal coherence and a compact memory footprint. On N3DV and MeetRoom, DecoGS achieves 34.55 and 31.60 dB PSNR respectively, outperforming all streaming and offline baselines, while rendering at 261 FPS with $70\times$ lower temporal flicker than the best prior method, requiring no large-scale pretraining.

An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports alone these are indistinguishable, and reinforcement learning theory shows that no amount of further experience separates them. The prescribed escape is richer data about the reporter itself. We ask whether a frozen language model, handed exactly that data, uses it. We build a two-option game in which a payout swap and a lying reporter produce byte-identical histories. Then we add one verified record: an independent check of one round's real result, printed beside what the reporter said about that round. That single line settles the case. We ask three large models, from two families, to answer one question with one letter. Is the reporter honest or lying? They catch a lying reporter almost perfectly. At the 70B class that holds in every condition we tried; the 32B model slips in one wording. They clear an honest reporter far less often, and how often depends on things that should not matter. Averaged over rounds, letters, and wordings, a 72B model calls an honest reporter a liar 38% of the time when nothing has changed at all, and 58% of the time when the payouts moved. A 70B model from a second family calls an honest reporter a liar 26% and 48% of the time. The failure is not one of reading, because in the situation where nothing changed the same models score 0.96 to 1.00 with the answer printed in the prompt. Which surface feature drives it differs by family. For the Qwen models it is which round the record names, and for Llama it is which letter stands for "honest." Adding the record to a prompt that already states the answer makes Llama less likely to give that answer. We had registered a prediction for that 58% before the run: 35%. The failure is larger than we expected.

Autonomous Software Engineering Agents (SWE-Agents) excel in deterministic coding tasks but struggle with Architecture 0, the nascent system design phase plagued by implicit engineering constraints, or Unknown Unknowns (UUs) that are rarely stated explicitly. To investigate how agents navigate UUs, we explore a progressive trajectory across pure-text self-play, tool-augmented feedback, and external physical mapping. Our empirical analysis reveals a cascading chain of failures. Pure-text reasoning inevitably devolves into polite consensus or plausible yet physically impossible fabrications. Attempting to bridge this gap via an early-stage execution sandbox unexpectedly triggers Specification Gaming: agents exploit their autonomy over validation scripts to bypass physical constraints, achieving superficial success without resolving core architectural flaws. To resolve this self-validation trap, we propose the Physical Mapping Guard (PMG). Grounded in the software engineering principle of Separation of Concerns, PMG revokes verification authority from the agent, forcing semantic intents to be evaluated by an external, deterministic Semantic-to-Physical (S2P) mapping engine. Extensive evaluations demonstrate that PMG completely eradicates physical-layer and validation-layer gaming. By precisely isolating residual failures to semantic reinterpretations and auditor overreach, PMG marks a critical step toward genuine affordance grounding in automated architectural design.

Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive interfaces between visual understanding and anomaly scoring. Caption-based pipelines compress visual evidence into text, potentially discarding subtle cues, while direct numerical generation forces the model to express its judgment through a small set of predefined scores. Such interfaces can obscure subtle differences in anomaly severity, causing visually distinct clips to receive similar representations or scores and thereby limiting the resolution of anomaly ranking. We propose \textbf{Probe-VAD}, an ordinal binary-probing framework that directly probes severity preferences from a frozen VLM. Given raw video clips, Probe-VAD queries ten ordered severity thresholds and extracts constrained \textit{YES}/\textit{NO} continuation likelihoods. Their normalized preferences form a cumulative severity profile, from which tail evidence is aggregated into a continuous anomaly score, with isotonic projection enforcing ordinal consistency. Experiments on public VAD benchmarks demonstrate superior performance with low computational cost. Probe-VAD provides a simple interface for translating frozen VLM visual understanding into continuous, rank-sensitive anomaly scores without task-specific training or caption-based compression. Code is available at: https://github.com/yvestine/COVAS-VAD.

Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of embodied policies, yet turning these algorithms into reliable robot systems remains constrained by fragmented data formats, training stacks, evaluation protocols, inference runtimes, and embodiment-specific interfaces. We present $\mathrm{FluxVLA}$ Engine, an open, configuration-driven platform that turns heterogeneous embodied-policy components into a reproducible data-to-deployment workflow. Rather than introducing another policy model, $\mathrm{FluxVLA}$ standardizes interfaces for datasets, visual-language and world models, action heads, reward- or advantage-weighted learning, distributed training, simulation evaluation, optimized inference, and robot operators. The engine further integrates compositional dual-arm simulation, scalable automatic data generation, and model-decoupled human-in-the-loop rollout, takeover, correction collection, and reward annotation. For responsive physical execution, it combines Real-Time Chunking (RTC) with accelerated inference backends, lightweight remote GPU serving, and configurable trajectory post-processing. Together, these capabilities connect offline learning, simulation validation, online correction, and real-robot execution through shared and auditable contracts. $\mathrm{FluxVLA}$ therefore targets the engineering bottlenecks separating promising embodied-learning algorithms from reproducible evaluation and dependable deployment. Code is available at https://github.com/FluxVLA/FluxVLA

Autonomous nano-UAV navigation requires accurate ego-motion estimation under stringent size, weight, power, and computing (SWaP-C) constraints, where visual sensors and LiDARs exceed payload limits, optical flow degrades in low-texture scenes, and inertial-only state estimation is susceptible to accumulated drift. While multi-zone time-of-flight (ToF) arrays provide a lightweight metric complement, 6-DoF estimation from merely 384 ranges per frame is challenged by invalid returns, anisotropic observability, and temporal computational scaling. We propose TIO-FORMER, a camera-free, optical-flow-free, and mapless range-inertial odometry framework driven by an IMU and an ultra-lightweight (15 g) payload of six orthogonal 8 x 8 ToF arrays. Our frontend pairs consecutive range grids with a bilateral gated difference, while IMU-guided cross-attention dynamically routes directional features conditioned on platform kinematics. A Streaming Causal Transformer couples an uncompressed Local KV cache with compressed Chunk-FIFO memory, maintaining bounded inference cost and memory footprint independent of flight duration. In real-flight evaluations, TIO-FORMER reduces open-loop position error by 54.4% compared to nano-UAV optical flow and by 66.4%-89.1% over learned inertial baselines. We also evaluate performance across multiple environments and robustness under severe sensing degradation. Deployed on an edge RISC-V companion computer, TIO-FORMER achieves a P95 latency of 10.466 ms and peak resident memory of 6.324 MiB (less than 5 percent system RAM), demonstrating that sparse range sensing provides practical geometric anchoring for resource-constrained micro-aerial robots. Code is available at https://github.com/Ly041021/TIO-Former.

Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed edge servers. However, heterogeneous communication and computing capabilities, together with dynamically evolving inference states, make the edge server selection for each incoming request time-varying and tightly coupled across slots. In this paper, we investigate an online request scheduling framework for edge LLM inference that jointly minimizes long-term average end-to-end latency and regulates workload distribution across heterogeneous edge servers. Two main challenges arise in this context. First, conventional latency models cannot accurately capture the fine-grained dynamics of multi-stage LLM execution. Second, the latency consequence of a scheduling decision is observed only after request completion, making immediate decision evaluation difficult. To address these challenges, we develop a cross-slot inference model that captures transmission, prefill, iteration-level decoding, and key-value (KV) cache evolution for each diverse request, and characterize server workload through a KV cache memory-time consumption metric. We propose the LYREO approach that transforms the long-term load-balancing constraint via Lyapunov optimization and employs reward redistribution with sequencebased return prediction to convert delayed outcomes into timely learning signals for earlier decisions. Simulations under various configurations demonstrate that LYREO consistently achieves lower latency and more balanced load distribution than representative learning-based and heuristic baseline schemes.

This article investigates data-driven policy iteration (PI) for continuous-time linear systems without requiring an initially stabilizing policy. Standard infinite-horizon PI is not self-starting because its policy-evaluation step is well posed only when the feedback gain is stabilizing. However, verifying this property is difficult when the system matrices are unknown. To remove this requirement, we develop a finite-horizon bootstrap method. The key idea is to perform policy evaluation over a compact interval for a shifted system, where the evaluation equation is well defined for arbitrary bounded time-varying policies. We show that, for a sufficiently long horizon, the initial-time optimal gain of the shifted finite-horizon problem, when applied as a constant feedback gain, achieves a prescribed stability margin for the original system. We then derive a data-driven implementation from an off-policy identity evaluated along trajectories of the original plant. We use basis-function approximations to reconstruct the finite-horizon value matrix and policy, and we characterize the resulting error through a perturbed policy-improvement recursion. A data-driven Lyapunov certificate is further introduced to verify admissibility of the candidate gain before it is used to initialize infinite-horizon PI. Numerical studies of a batch reactor and a two-mass-spring system demonstrate the effectiveness of the proposed bootstrap method.

3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot interaction and AR/VR. Although conventional cameras have been widely adopted for this task, methods that rely on them struggle in low-light environments and under severe motion blur. To address these limitations, event-based cameras have recently attracted attention for their high dynamic range and high temporal resolution. However, applying event cameras to egocentric hand reconstruction remains challenging because camera wearer's motion produces dense background events that obscure hand-specific signals. Although the first egocentric event-based approach mitigates this issue using hand segmentation, its binary hand mask does not distinguish between left and right hands. As a result, the model lacks instance-level hand information and predicts both hands even when only one or neither hand is present. This limitation leads to incorrect inter-hand relationships and degraded reconstruction accuracy. In this paper, we propose EventEgoHands++, a framework for event-based 3D hand mesh reconstruction from an egocentric viewpoint. The proposed method incorporates a Hand Detector that estimates instance-level bounding boxes and masks for both the left and right hands. Moreover, we introduce Adaptive Attention, which dynamically gates the attention based on these detection results to accurately learn the spatial relationship and mutual interactions between the hands. To train and evaluate our framework, we extend the synthetic N-HOT3D dataset and newly construct EEH-R, the largest real-world event-based egocentric hand dataset to date, comprising approximately 1M annotated frames captured in environments including low-light conditions. Extensive experiments on both synthetic and real datasets demonstrate that our method consistently outperforms the baselines.

Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurrent depths. However, they incur higher decoding latency than standard Transformer models of comparable parameter size because shared weights are accessed at every recurrent depth. To improve decoding efficiency, self-speculative decoding is particularly well suited to Looped Transformers, as their intermediate recurrent states can directly provide draft predictions without an auxiliary draft model. We therefore propose LoopSpec, a training-free self-speculative decoding framework tailored for Looped Transformers. LoopSpec extracts draft tokens from early recurrent states and operates in a pipelined manner, overlapping draft generation of future tokens with target verification of the current token. To improve draft accuracy without excessive compute overhead, we introduce a selective second proposal from deeper recurrent depth while ensuring lossless decoding under both greedy and sampling regimes. Furthermore, we derive the optimal proposal depths in closed form and show the prediction matches measurement. Across reasoning and coding benchmarks, LoopSpec achieves up to 6.83$\times$ inference speedup across diverse Looped Transformers.

We present IRENE (Italian Radar Ensemble Nowcasting Experiment), a deep learning model for probabilistic short-range precipitation nowcasting over the Italian domain at \SI{1}{km} spatial and 5 min temporal resolution. IRENE adopts an encoder--forecaster architecture built on multi-scale Convolutional Gated Recurrent Units (ConvGRUs), trained on the national radar composite produced by the Italian Civil Protection Department (DPC). An importance-sampling scheme focuses training on precipitation-relevant events, while the almost-fair Continuous Ranked Probability Score (afCRPS) is adopted as the primary probabilistic loss function. Two additional training configurations are proposed: an adversarial (GAN) variant, IRENE-GAN, designed to improve the spatial sharpness of the generated forecasts, and a spectrally constrained variant, IRENE-GAN-RAPSD, in which the adversarial objective is complemented by an explicit penalty on the radially averaged power spectral density. The three configurations are evaluated against the stochastic extrapolation method STEPS and the pre-trained deep learning model DGMR. All IRENE configurations attain a lower Continuous Ranked Probability Score than both benchmarks at every lead time and rank histograms closer to uniformity, indicating better probabilistic skill and ensemble calibration. In terms of ensemble-mean mean absolute error the advantage is confined to the first 90 min, beyond which the strongly damped DGMR fields and, to a lesser extent, STEPS become competitive. Spectral analysis shows that the adversarial training removes the progressive loss of small-scale variance exhibited by IRENE, at the cost of an excess of fine-scale power at long lead times that the spectral penalty only partially controls.

A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment. We show how an anthropomorphic hand can learn these skills while retaining its finger design and position controller. Onboard power and computation make the platform self-contained. Our reinforcement learning approach accounts for the hand's unequal fingers, with training in a simulator calibrated from hardware measurements. In simulation, the hand moves faster with our reward formulation than with tuned rewards originally designed for quadrupeds. On hardware, task-specific policies enable untethered crawling, steering, and fall recovery. While supporting its own weight, the hand also executes successive keyboard commands without vision and pushes an object to targets using overhead visual feedback. These results demonstrate a compact mobile manipulator that reuses its fingers for locomotion and interaction, without a separate locomotion mechanism.

Autonomous systems require reliable place recognition for efficient and effective simultaneous localisation and mapping (SLAM). Traditional geometric visual SLAM approaches rely on low-level features and geometric consistency, but remain vulnerable to perceptual aliasing, where different places appear similar, and perceptual variation, where the same place appears different. Although semantic SLAM and modern learned visual place recognition (VPR) methods improve robustness under challenging perceptual conditions, real-time deployment requires both high retrieval accuracy and low latency. Inspired by human memory and perception, we propose HuMem-VPR, which exploits the bidirectional relationship between bottom-up perceptual evidence and top-down contextual reasoning to achieve high-level place understanding. We further introduce HuMemSLAM, the integration of HuMem-VPR with ORB-SLAM3. HuMem VPR achieved the highest aggregate retrieval accuracy on the real-image benchmark, competitive accuracy on the CARLA benchmark, and approximately two to three times lower latency than the evaluated state-of-the-art VPR methods. Across the evaluated dataset families and online experiments, HuMemSLAM substantially improved integrated Recall @1 over ORB-SLAM3's native retrieval while reducing the proposals submitted to its geometric backend.

Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable remains challenging. Layer-wise Relevance Propagation (LRP) has been adapted to transformer attention, but in ViTs it often produces noisy, unfaithful explanations. We show that the missing ingredient is the treatment of residual connections: cancellation effects in residual pathways lead to attribution explosion. Moreover, we find that these cancellations are substantially stronger in ViTs than in language transformers. To address this issue, we introduce Residual-aware Layer-wise Relevance Propagation (ResLRP), a simple extension of LRP whose propagation rules explicitly account for cancellations in residual branches, are exactly conservative, and provably bound relevance explosion. Causal channel-wise interventions confirm that residual cancellation, not a generic regularization effect, drives the instability. ResLRP substantially improves attribution quality across faithfulness and localization, evaluated on ViT architectures spanning supervised, self-supervised, contrastive, hierarchical, and multimodal families, as well as on the ground-truth-controlled FunnyBirds benchmark. The largest gains arise in modern Vision Language Models (VLMs), with +27-29% localization and up to 3.4x faithfulness scores. Beyond benchmarks, ResLRP localizes Sparse Autoencoder (SAE) features in input space, and our residual amplification measure serves as an architecture-level diagnostic predicting where attribution degrades.

We study an optimal intervention problem for linear threshold models. This is a popular class of dynamical network systems whereby a number of agents, identified with the nodes of a graph, strategically change their binary action (0 or 1) according to a threshold rule. Specifically, an agent adopts action 1 if and only if the fraction of its neighbors in the interaction graph that do so is greater than or equal to a prescribed threshold. Assuming that a planner can modify the agents' thresholds at a cost equal to the aggregate threshold increase, we study the minimum intervention cost needed to ensure global convergence to the all-1 configuration. Our main contribution is the introduction of a new graph-theoretic quantity, called oriented path number, that is the minimum number of disjoint paths needed to cover the graph that can be oriented to form a directed acyclic graph. When thresholds are all equal to 1/2, the optimal cost is shown to coincide with the oriented path number, whereas, in the general case, it turns out to be the main ingredient of a bound on the optimal intervention cost.

Dynamic facial expression recognition (DFER) benchmarks such as DFEW provide multiple annotator votes per clip, yet most models collapse them to a majority label and cannot represent human disagreement at inference time. We propose a disagreement-aware DFER framework that trains directly on the raw annotator count vector using a Dirichlet-Multinomial likelihood. Unlike mean-only soft-label objectives, the proposed likelihood provides scale-sensitive supervision for the Dirichlet concentration while preserving the predictive mean. A separate ambiguity head predicts annotation entropy for unseen clips, and a monotone Chow-style reject rule combines predicted ambiguity, vacuity, temporal instability, and input quality for selective prediction. On DFEW, the method preserves recognition accuracy while reducing ECE by 30% and AURC by 15%, and predicted ambiguity reaches a Spearman correlation of 0.52 with the annotation entropy of test clips. The calibration and selective-prediction gains transfer to FERV39k and remain under identity- and movie-disjoint DFEW splits.

Comprehensive structured data on inter-firm relationships is often scarce or inaccessible because many relationships are privately negotiated, selectively disclosed, and fragmented across proprietary databases. This scarcity hinders the discovery of collaboration opportunities, particularly for startups and small and medium-sized enterprises. Firm profiles are readily available, but collaboration potential cannot be inferred from business similarity alone, since similar firms may be competitors, whereas dissimilar firms may offer complementary products, technologies, channels, capabilities, or capital. We present FirmCORe (Inter-Firm Collaboration Opportunity Reasoning), a human-annotated benchmark for pairwise reasoning over weakly structured firm profiles, comprising 2,805 labeled firm pairs. Given two firm profiles, a model must determine whether the available evidence supports a collaboration opportunity and, for positive pairs, jointly predict its strength, primary collaboration type, and role direction. FirmCORe also provides parallel Chinese- and English-language evaluation sets containing identical instances and gold labels, enabling controlled analysis of input-language sensitivity. Experiments with representative locally deployed and hosted large language models (LLMs) show that the strongest model achieves a macro-F1 score of 74.51 for opportunity detection but only 61.57% exact match across all four output fields. Language effects vary across models, and high cross-language agreement can mask errors shared across languages. These results indicate that current LLMs are substantially more reliable at detecting broad collaboration opportunities than at identifying their specific types and role directions.

Thermal optimization of 2D CFET inverters requires testing structural proposals against their electrical costs. We examine these research tasks using an AI agent workflow within a supplied electrothermal model. At 12 nm, Astra selects a redistributed source-interconnect geometry, while a coordinating agent proposes a substrate-directed heat-removal path. The combined design reduces peak temperature rise by 1.67 K at fixed metal volume and 20 μW. A subsequent metal-resistance sensitivity gives about 0.6-K inverter cooling alongside a 2% nFET on-current loss. Effective contact-length scaling further shows that lower temperature can accompany higher thermal resistance when current falls. Reproduction identifies agreeing implementations and retains a 104.95-K failure for diagnosis. These results show that an AI scientist workflow can propose thermal structures, test them under common constraints, and quantify their electrical cost.

Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution. Intrinsic Robot Rewarding (IRR) proposes to use these resources for a second, complementary purpose: evaluating the robot's own outcomes and providing feedback for policy improvement. Successful demonstration endpoints define task-specific references, and the policy's frozen visual encoder provides the feature space in which new outcomes are assessed. The core reward mechanism adds a reference bank and a scoring operation to the existing pipeline, without requiring a separate learned evaluator or an additional perception backbone. Our position is that this reuse offers a promising route to lower integration effort, efficient reward computation, and reduced recurring human outcome scoring. Building on established research in visual rewards and learning from experience, IRR brings these ideas into the robot's existing perception and demonstration pipeline. An operational COMAU Racer 3 demonstrator is available at technology readiness level 4 (TRL 4). This laboratory foundation supports the next research step: connecting internal outcome evaluation to physical policy improvement. We present the reward formulation, central research questions, and an evaluation methodology linking reward reliability to task success and supervision effort. The intended contribution is a reusable approach to learn and improve from the data and experience already available in industrial robot systems.

Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained text and vision encoders. The usefulness of such models have also been demonstrated on a wide range of benchmarks, with an important caveat - the dominant approach in these benchmarks evaluates multiple choice reasoning via text options. This is a natural way to test text-based reasoning in these models, and has led to significant insights regarding model behavior in the community. In this work, we ask a different question - what happens when the evaluation modality is visual, rather than text? We introduce three new vision-centric evaluation benchmarks in temporal frame retrieval, video future prediction, and causal memory distortion, all designed around evaluating visual understanding capabilities in large video models. Our approach complements the existing approaches to evaluate video understanding in frontier models. We show that current frontier models exhibit significant weakness when attempting to reason through visual queries, rather than text. We conclude with an extended analysis section that provides pointers for future improvements in visual understanding for large video models.

A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We study a narrow, practical question: for already-trained standard LoRA adapters -- not adapters retrained for cache compatibility -- how much task quality is preserved if the backbone's prefill KV cache is computed once and reused across specialists, and what does that buy in serving cost? On a Qwen3-1.7B backbone with two adapters (extractive QA on HotpotQA, arithmetic reasoning on GSM8K), we sweep the boundary at which the specialist takes over from the reused base cache and measure paired quality differences and serving cost. Full-prefix reuse had the lowest prefill cost and a small quality difference on held-out GSM8K (Delta = -4.6 EM at a 160-token budget; -3.0 at 320 tokens; -0.8 under a second training seed -- all favoring native, only the first excluding zero, and the magnitude not consistent). Partial recomputation provided no demonstrated advantage. Neither quality equivalence nor a general boundary-selection rule is established. We also report a closed-form ridge KV translator that did not beat direct reuse, and specialist-dependence contrasts whose intervals all include zero. The measured serving benefit is warm-cache time-to-first-token, which grows with context (~16x at 8K); two-branch peak memory was only 12% lower and, on inspection, the prefix was never physically shared across branches -- this implementation reuses KV values but copies their storage, so shared-cache memory savings are not achieved.

Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and tool-using agents stay unreliable: even frontier models answer little more than half of real-world database questions, and far fewer of the multi-step, operational ones, because the LLM must compose how heterogeneous sources relate and hallucinates the relations, not just the fields. We propose symbolic separation: a deep agent reasons freely but may act on data only through an ontology-constrained Virtual Knowledge Graph with deterministic pre-execution validation. Unlike a tool API's interface contract, this domain-semantic contract turns a complex question into one validated graph traversal instead of LLM-inferred joins. Instantiated as the Neurosymbolic Deep Analyst and evaluated on 49.9 TB of superconputer telemetry against a rigid workflow and a non-symbolic ablation, it raises end-to-end task success from 43% to 86%, prevents silent data-integrity errors that no syntactic check catches, and cuts token cost by 2.4x, letting a smaller on-premise model outperform a larger one.

Detecting and grasping small objects remains a significant challenge in robotics. Active vision, where the robot moves closer to the object, is an intuitive solution, yet comparing approaches on common ground is difficult since identical physical scene setups are required. Hence, we introduce BRAVE-6D, a benchmark designed to evaluate robotic active vision systems for object pose estimation, a crucial first step in grasping objects. BRAVE-6D leverages view synthesis based on Gaussian Splats (3DGS) to provide scenes and tools for benchmarking active vision systems. We show baseline solutions performing visual servoing within the scene and accurately estimating the poses of small objects.

Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconstruction alone can entangle manipulation-related motion with appearance changes and camera movement. We present GeoLAM, a framework for learning geometry-grounded latent actions from action-free human videos. GeoLAM combines future-frame reconstruction through a frozen geometric feature hierarchy with motion supervision from a training-only 4D geometry teacher. The geometric representation provides a structural prior, while the teacher's predictions yield spatially pooled targets capturing 3D displacement, residual image-plane motion, and surface-orientation changes. Visibility and confidence weighting reduces the contribution of unreliable estimates, encouraging continuous latent actions to retain geometric motion without explicit hand-pose or hand-trajectory annotations. After video pretraining without action labels, the learned representation provides transition targets for a world-action model trained on action-labeled robot demonstrations. The model jointly denoises latent actions and executable action chunks, with future-video prediction used only as an auxiliary training task. Deployment therefore requires neither the geometry teacher nor future-video generation. Evaluations on a latent-action benchmark and robotic manipulation tasks demonstrate the strong performance of GeoLAM.

Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approaches typically adopt a static heuristic paradigm, where information is passively archived without adaptive memory valuation. Consequently, these methods fail to self-evolve or align their memory management with evolving user needs. To address this, we propose ICML (InteraCtive Memory Learning), a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy. Specifically, we first employ a session synthesis pipeline to generate expert data, facilitating rapid test-time adaptation in unseen scenarios. Building on this, ICML utilizes an online reinforcement learning mechanism where a Planner agent selectively encodes high-value information and a Trigger agent dynamically retrieves it to optimize response quality, whereby the two agents co-evolve through continuous interaction feedback. Crucially, both agents are synchronized through a delayed reward mechanism that propagates future feedback back to earlier storage decisions, ensuring memory policies are precisely aligned with user expectations. Experimental results demonstrate that ICML significantly outperforms strong baselines, exhibiting the unique capability to continuously improve response quality as interactions accumulate.

Grounded language-model systems are often evaluated by final answer accuracy, yet a correct answer can be unsupported, drawn from the wrong source, or produced when evidence is insufficient or contradictory. We introduce EviScope, a paired counterfactual benchmark that holds the question fixed while adding, removing, distracting, or contradicting its evidence. EviScope-v1.1 contains 40 four-condition quartets with repaired counterfactual claims and span-level support labels for automatic evaluation. Across 960 gold-blind generations from Qwen2.5-7B, Llama 3.1 8B, and Gemini 3.5 Flash, paired metrics expose model-dependent grounding behavior that answer accuracy hides. On two local open models, an explicit evidence-action gate underperforms vanilla RAG on QCS: 0.15 vs. 0.50 for Qwen and 0.10 vs. 0.375 for Llama. Gemini reaches 0.944 joint success under both prompts, yet still answers 5% of conflict cases after contradiction insertion. EviScope therefore distinguishes unsupported answering, conflict blindness, and wrong non-answer actions rather than scoring answers alone.

Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference from a partially observed multimodal episode together with structured prediction of the remaining behavior, rather than exact motor forecasting. A compact Hierarchical Planning Decoder (HPD) is attached to a frozen neuro-symbolic recognition encoder and predicts, at four ontological levels, the next actions, the remaining activities and low-level intentions, and the episode high-level intention(HLI). The decoder is trained with soft neuro-symbolic regularization combining transition-coherence and hierarchical continuity losses, and is decoded with hard reachability masks that enforce ontological validity at inference. On a compositional four-level benchmark of 15,002 multimodal episodes built over NTU RGB+D 120 features, three headline properties are observed together. The advantage over the strongest sequential baseline grows with the anticipation horizon, from +1.7 points at step 1 to +7.3 points at step 3 (top-5). Under compositional generalization, where one parent association per multi-parent low level intention is held out, this advantage widens to +4.9 points at step 1. At the episode level, 96.8% of anticipated trajectories satisfy the joint logic constraints, above the 88.1% strongest-baseline value and the 73.9% ground-truth floor; soft logic terms alone account for a 59.8 to 71.1% relative reduction of HLI-reachability violations, and the hard masks then eliminate them entirely. Neural generation supplies predictive ranking, symbolic constraints supply onto logical validity, and their combination yields coherent hierarchical anticipation while exposing remaining challenges in compositional goal generalization and unordered set prediction.

Asset Administration Shells (AAS) provide a standardized means of representing assets and their information in manufacturing and increasingly serve as a basis for software services. However, different AAS instances vary in structure, content, and degree of completion, making it difficult to determine whether a given AAS is suitable for a specific application. This paper presents two complementary methods to support the comparison and application-oriented assessment of AAS. First, set-theoretic operations are employed to compare AAS models, enabling the identification of common, missing, and differing submodels and parameters. Second, an AAS suitability model assesses the conformity of an AAS to the requirements of a specific use case. The assessment considers structural conformity, semantic consistency, cardinality, and specification conformity and can be performed either against a reference AAS or a set of required SemanticIDs. A suitability value is derived from the identified deviations and is complemented by a detailed report of missing or non-conforming information. The proposed approach support practitioners and researchers in the comparison of evolving AAS and provide application-specific information on their suitability for manufacturing software services.

Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn graph representations. However, their discriminative power is upper-bounded by the Weisfeiler--Lehman (1-WL) graph isomorphism test. This prevents GNNs from distinguishing certain non-isomorphic graphs with identical local neighborhood structures, often leading to similar graph representations. Unified Topological Signatures (UTS) capture compact, multi-scale representation of global graph topology derived from persistent homology. We introduce two complementary UTS signatures: Graph_UTS- a static signature of the input graph topology, and Embedding_UTS- a dynamic signature of the evolving embedding topology. They encode structural information inaccessible to 1-WL-based message-passing GNNs, yet their capabilities are explored solely for post-hoc embedding-space analysis. We integrate UTS into GNN training across three architectural interventions: (i) UTS-Aug: augmenting with standard readout feature that encodes graph's true topology; (ii) UTS-Reg: topological regularizer that constrains representation collapse; (iii) UTS-Pool: topology-guided pooling that retains structurally critical nodes. We further leverage UTS as a layer-wise diagnostic to quantify oversmoothing during GNN training. Theoretically, we show that integrating UTS into GNN optimization strictly extends GNN expressivity beyond the 1-WL hierarchy. Experiments on three graph classification benchmarks show consistent benefits: Graph-UTS, Dual-UTS, and UTS-Pool improve accuracy across all three datasets, Embedding-UTS provides smaller but similarly consistent gains, and UTS-Reg's benefit varies across graph domains. Accuracy improves by up to 5.8% with Graph-UTS augmentation, by up to 1.9% with UTS-Reg, and achieves comparable performance to TOGL with UTS-Pool.

Current predictive turn-taking models (PTTMs) achieve strong performance on benchmarks with controlled acoustic conditions and clean audio signals. Their generalisation to conversations with overlapping speech and background interference remains underexplored. In this research, we evaluate audio-visual PTTMs trained with clean data on a challenging cocktail-party testbed derived from the AVCocktail dataset, and analyse their adaptation behaviour to this new domain. Experimental results show consistent performance degradation across audio and visual modalities under noisy conditions, with up to 38% relative drop in weighted F1. Fine-tuning on the new domain improves robustness, but gains vary across modalities and depend on the size of the available pre-training data. These findings provide insights into the different generalisation and adaptation capabilities of the audio and visual modalities, and indicate the need for robust modelling strategies to adapt to the complexities of human interactions in noise. All code and turn labels are made publicly available to facilitate further research.

Multi-hop question answering requires combining information from multiple documents to answer complex questions. These systems have grown increasingly capable, yet when they fail, the error is typically attributed to not finding the right documents. Whether this holds at the level of individual reasoning steps remains largely unexamined. We investigate this across three standard multi-hop QA benchmarks and find that failures decompose into two distinct modes: retrieval failures, where the needed passage was not retrieved, and extraction failures, where the passage was retrieved but the needed fact could not be extracted - a phenomenon we term the fact-grounding gap. Extraction failures account for nearly half of all per-hop deficiencies and are invisible to standard retrieval metrics. They remain unresolved by every retrieval intervention we test, establishing a ceiling for retrieval-only improvements. The gap's severity varies across benchmarks and question types, but extraction failures appear on every dataset we measure. Our findings reveal that retrieval failures and extraction failures are fundamentally different bottlenecks requiring different solutions - a distinction absent from current evaluation practice.

Wild test-time adaptation (WTTA) updates a source model online under small test batches, concurrent distribution shifts, and time-varying class imbalance. Most WTTA methods derive their adaptation signals, including predictive uncertainty, sample reliability, and local feature geometry, from the model being adapted. When the source model is unreliable under shift, these signals can reinforce its own errors, forming a self-referential loop. We introduce MASA (Multimodal-LLM-Anchored Semantic Adaptation), which complements model-internal evidence with structured semantic descriptions from a frozen multimodal large language model (MLLM). To limit inference cost, MASA queries the MLLM only for a small set of diverse, reliability-ranked anchors. The resulting descriptions capture the object family and nuisance factors such as style, viewpoint, and occlusion. MASA encodes these descriptions, propagates them to neighboring test samples, and stores the resulting visual-semantic information in an online prototype memory. Descriptor-aware retrieval from this memory provides an auxiliary target for lightweight adaptation of normalization-affine parameters. We evaluate MASA on the WTTA ImageNet-C benchmark under limited-batch, mixed-domain, and imbalanced-label-shift settings with ResNet and ViT backbones.

Sparse-view 3D scene reconstruction with 3D Gaussian Splatting (3DGS) is inherently underconstrained. Plausible renderings can also coexist with erroneous Gaussian geometry, as errors in positions or depths may be concealed by opacity, scale, and appearance; we term this failure mode Geometry Cheating. Existing regularization methods constrain geometry but remain limited to observed views, while video-diffusion-based methods complete unseen views yet mainly use them as RGB pseudo-supervision, underusing motion and temporal priors and lacking explicit geometry supervision. We present Bi-FlowGS, which uses optical flow to bridge generative view completion and Gaussian geometry regularization. Our plug-and-play Video-to-Geometry Flow Distillation (V2G) distills temporal correspondence priors from restored videos into Gaussian geometry to alleviate Geometry Cheating. Conversely, Geometry-to-Video Flow-Guided Restoration (G2V) uses the current 3DGS geometry to guide temporally consistent video restoration, providing more reliable generative supervision. Together, V2G and G2V form an implicit bidirectional co-refinement process, enabling restored videos and the optimized 3DGS scene to iteratively improve each other. Experiments demonstrate improved rendering quality and geometric consistency across wide-baseline and unbounded 360° benchmarks.

Soft and continuum robots enable manipulation through distributed body deformation and contact, yet translating language and visual context into executable whole-body actuation remains a fundamental challenge. We present SWIM, a framework that maps an initial RGB observation and a language instruction to a complete actuation-command sequence. Its vision-language-action (VLA) policy, SWIM-VLA, combines a diffusion action head with Visual Soft Proprioception (VSP) through a shared representation of RGB observations, language instructions, and tendon states. The diffusion head models conditional distributions of expert command chunks, while VSP supervises ordered body-anchor predictions using simulation ground truth, encouraging the representation to retain body geometry when learning from limited demonstrations. Embodied mechanical intelligence supports physical execution of command sequences generated through iterative virtual rollout from evolving simulated observations, with intrinsic compliance providing local contact adaptation without online policy queries. We evaluate SWIM on packing, reaching, and grasping on a planar tendon-driven soft robot, with grasping targets anchored. In simulation, SWIM-VLA achieves success rates of 100\%, 96\%, and 88\%, respectively, outperforming an adapted OpenVLA-OFT baseline and controlled ablations. On hardware, SWIM achieves success rates of 100\%, 80\%, and 75\%, compared with 75\%, 40\%, and 25\% for direct online deployment of the same policy checkpoint.

Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a data stream without catastrophic forgetting. While leveraging pretrained models has significantly advanced continual learning, existing methods exhibit a scalability bottleneck when trained sequentially on many tasks, suffering from performance degradation due to inter-task interference and loss of plasticity. Inspired by evidence that sparse fine-tuning achieves performance comparable to full fine-tuning, this paper presents a novel sparsity-driven continual learning framework. Our continual learning method, termed CLARE, operates in two stages: it first identifies a sparse, task-critical parameter mask via a sparsity-inducing objective, then performs mask-constrained fine-tuning by only optimizing parameters selected by the mask. This two-stage sparse adapter mechanism enables all tasks to be accumulated within a shared adapter space while reducing destructive interference across tasks. Extensive experiments demonstrate the scalability of CLARE. On the long task-sequence benchmark Omnibenchmark-1k, CLARE outperforms strong baselines in final accuracy by a large margin, e.g, improving EASE by 4.64% and 13.34% after learning 100 tasks, respectively.

Autonomous wheel-loader control requires joint reasoning over task semantics, egocentric vision, proprioception, and 3D scene geometry. We present sensVLA, a Vision-Language-Action (VLA) architecture that combines a Qwen3-2B Vision-Language Model (VLM) with a fully trainable transformer action expert trained by flow-matching velocity regression. sensVLA routes Bird's-Eye-View (BEV) features, extracted from fused front and rear lidar, directly to the action expert through a dedicated cross-attention pathway, while the VLM consumes front and rear RGB views to provide task-conditioned semantic context. This design decouples spatial grounding from linguistic reasoning while preserving interaction between both streams at decision time. The expert predicts six action dimensions: longitudinal velocity, steering, body-frame displacement, arm rate, and bucket rate. On a real-world dataset from a wheel loader, sensVLA reaches aggregate per-step parity with a strong camera-only baseline and reduces longitudinal velocity RMSE by 28% and displacement error by 9% on loading centric scenarios. It also degrades 29% less when the camera stream is corrupted or removed, evidencing that explicit spatial grounding improves accuracy and fault-tolerance for heavy equipment autonomy.

Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a model is only valuable if it learns semantically meaningful and trustworthy patterns rather than exploiting spurious correlations. Conventional evaluation practices predominantly assess predictive performance. Consequently, whether the model relies on semantically meaningful patterns remains unknown. To address these challenges, we adapt the knowledge generation framework for network traffic classification. The adapted framework combines data, ML models, explainability, visualization, and expert reasoning to support the iterative exploration, verification, and refinement of model behavior and data preprocessing. The framework is grounded in findings from the literature, benchmark dataset analyses, practical experience with XAI-based traffic classification, and expert feedback, providing practical guidance for semantic model validation. By complementing predictive performance with semantic validation and human expertise, the proposed framework supports the development of network traffic classification models that are not only accurate but also robust and trustworthy.

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-selection strategies. As a result, configurations that are effective for one family of queries often perform poorly for others. In this paper, we introduce ORDER (Optimal Routing for Dynamic Evidence Retrieval), a query-conditioned RAG framework that jointly adapts indexing and retrieval to the incoming query. Our approach first discovers semantic clusters over a given set of questions associated to a corpus and learns, for each cluster, a chunking strategy together with a suited metadata filtering and reranking configuration. At inference time, queries are routed to the appropriate pre-built index through nearest-centroid assignment. To further improve retrieval, we propose a supervised query router (QRe) that predicts which collections are most likely to contain relevant evidence, coupled with a Uniform Multi-source Sampler (UMS) that allocates the retrieval budget evenly across the selected sources. We evaluate our framework on large-scale, heterogeneous historical archives and show that conditioning both indexing and retrieval on the query consistently outperforms both naive baselines and strong state-of-the-art RAG systems in complex expert-domain environments.

Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a severe information bottleneck, often losing subtle behavioral patterns and emotional shifts. Furthermore, being typically static post-deployment, they cannot autonomously adapt to personal habits and preferences without manual feedback. Cognitive science, however, suggests that humans maintain mental models purely in a latent space and continuously refine them through predictive coding. Inspired by this, we propose \textbf{ThinkFlow}, a novel end-to-end latent memory framework for lifelong conversational agents. ThinkFlow bypasses the text bottleneck by dynamically compressing conversational flows into probabilistic latent memory skills, autonomously consolidating complex user states into disentangled, continuous vectors without semantic interference. To break this barrier, we introduce a test-time evolution paradigm. By coupling teacher-guided latent alignment to bootstrap the initial state with a self-supervised next-user-utterance prediction task for continuous refinement, the framework successfully overcomes cold-start challenges and achieves label-free lifelong personalization. Extensive experiments on long-term conversation benchmarks demonstrate that ThinkFlow significantly outperforms prevailing memory systems, providing highly personalized and contextually accurate responses over extended multi-session interactions.

Large language model (LLM) inference is often constrained by both computation and memory, especially in offloading-based deployments where model weights are transferred across memory hierarchies during autoregressive decoding. In this setting, reducing the number of executed layers can lower per-token latency while also avoiding costly weight movement. Motivated by this observation, we present FlexEE, an early exiting framework for resource-constrained and offloading-based LLM inference. FlexEE makes early exiting practical for LLM decoding through layer-wise exit supervision for reliable intermediate-layer prediction, self-speculative decoding over a Top-K local vocabulary for low-cost exit decisions, and dynamic hidden state management for KV-cache-correct and memory-aware execution. Across generative and downstream tasks, FlexEE enables efficient early exit with minimal accuracy degradation, delivering up to 1.27$\times$/3.16$\times$ and 1.25$\times$/2.83$\times$ end-to-end speedups on Llama2-7B and Llama3-8B under 0\%/50\% weight offloading, respectively.

Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapidly. We introduce UNRESTSENT200K, a Bangla crisis sentiment dataset with approximately 200K Facebook and YouTube comments from the July-August 2024 Bangladesh uprising. The dataset covers five event-aligned phases, from early escalation and internet blackout to regime transition and a later flood crisis. Each comment is linked to its parent post, enabling evaluation with and without discourse context. All comments are annotated through a fully human process involving 14 native Bangla-speaking annotators and senior validation, achieving substantial agreement (kappa = 0.73, alpha = 0.71) and 94.2% blind-audit agreement. We benchmark fine-tuned encoders, prompted LLMs, and LoRA-tuned LLMs. Results show that parent-post context consistently improves performance, while temporal shift across phases causes large performance drops. Strong LLMs perform well, but still struggle with sarcasm, implicit political references, and phase-dependent meaning. UNRESTSENT200K provides a benchmark for studying context-aware and temporally robust sentiment analysis in low-resource crisis discourse. UNRESTSENT200K is available at https://sami0055.github.io/UNRESTSENT200K/

Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such issues in drafts through careful, traceable feedback, yet advisor-style assessment requires extensive manual effort and does not scale. To shift automated paper assessment from a judge to a diagnostician, we introduce PaperDoctor, an agent framework for pre-submission feedback with three key innovations. First, a holistic hierarchical framework evaluates writing, layout, references, code, theory, prior work, and experiments through three layers: L1 surface screening, L2 typed verifiers that route each claim to the appropriate evidence, and L3 reproducers that rerun experiments by priority. Second, each finding contains an observation, a pointer to specific evidence such as a sentence, equation, or code line, and a revision suggestion, making critiques auditable and actionable. Third, PaperDoctor selectively rebuilds and reruns experiments based on claim importance and compute budget, surfacing reproducibility gaps and quantitative limitations that are invisible from the manuscript alone. We evaluate PaperDoctor on 30 in-progress papers, yielding 70.6% agreement and all positive holistic scores, and on 40 manuscripts across machine learning, natural science, and social science, covering human- and AI-authored papers with code. Overall, PaperDoctor produces more auditable feedback than human and other agentic reviewers, pairs critiques with concrete suggestions by design, and complements dimensions often overlooked by human reviewers. We also develop an interactive interface that lets authors browse findings grounded in their paper. PaperDoctor reframes automated paper assessment as diagnosis rather than verdict, taking a concrete step toward AI advisors for more rigorous AI-assisted scientific discovery.

Natural language arguments are compelling before they are formally explicit. A premise supports a claim through defeasible warrants, background commitments, and exception conditions that the text leaves implicit. However, formal verification requires the opposite. Making such arguments machine-checkable requires constructing the missing commitments, not only translating given sentences into logic. Construction, however, carries a risk that translation does not: a system free to add premises can make any claim provable, and a formally valid proof may assert the claim outright, prove it without the original premise, or establish more than the claim itself. We address this problem by formulating autoformalization for argumentative material inference as guard completion, in which non-monotonic material support is turned into monotonic formal inference relative to an explicitly constructed guard set. A completion is accepted only when its proof both passes the theorem prover and survives contrastive tests of premise dependence and claim selectivity. We implement this formulation in GUARD, a neuro-symbolic framework in which LLMs construct and formalize candidate guards, Isabelle/HOL verifies the resulting theories and returns step-level feedback for iterative refinement, and the system abstains when no faithful completion can be reached. Our empirical results on Debatepedia and ARCT using different LLMs demonstrate that GUARD yields significant improvements in verified-faithful (+35.3, +32.9 points) and substantial reductions in leakage (-25.9, -21.9 points) over the state-of-the-art LLM-driven theorem proving approach. Moreover, we show that the symbolic soft critique and the explicit assumption layer account for most of these gains, with the soft critique also improving the initial validity of the elicited context and reducing the number of iterations required for successful verification.

LLM-based multi-agent systems can fail even when communication succeeds because agents do not correctly track their peers' roles, knowledge, or intentions. We investigate whether such inter-agent misalignment cases, labelled FC2 in MAST-Data, can be converted into functional partner-state reasoning items. ToMAS applies four explicit convertibility criteria to diagnosed execution traces. A full conversion pass over 242 eligible non-AG2 training traces produced 39 CLEAN items. In an 18-trace reliability pilot, two annotators achieved 94.4% raw agreement and Cohen's kappa = 0.92. We then used the converted items as binary rewards in a small-scale GRPO feasibility experiment with Qwen2.5-1.5B. On a 28-item held-out Magentic GAIA diagnostic, every evaluated condition exceeded the ROUGE-L threshold on the same 2 of 28 items. Post-hoc adapter checks show why: under the learning rate used, the LoRA update remained numerically negligible (max abs Delta W about 7e-6), so all conditions decode identically to the untrained checkpoint. The experiment therefore does not show a training effect and cannot establish one; it reports an executable pipeline together with two limitations that any conclusive study must address: a provenance gap between the training and evaluation items, and lexical-overlap scoring. ToMAS provides a preliminary rubric and pipeline for converting diagnosed coordination failures into trainable partner-state reasoning items and identifies the requirements for a conclusive matched-domain evaluation.

Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the reserved identifiers the model obeys. Anyone who controls text in a prompt can therefore write a turn boundary indistinguishable from one the serving stack wrote. We audit 256 deployed chat tokenizers. All are forgeable, and the flag usually recommended as a fix leaves 56.6% forgeable because it misses the tool and reasoning markers agent systems rely on. We propose nameless tokenization, which leaves the control entries with a reserved identifier and no surface string, so the content encoder cannot emit one and message content reaches the model unaltered. Across five tokenizer families it reproduces the standard token stream exactly on attack-free data and lifts accuracy on a probe of delimiter-bearing text from 8.5% to 59.9%, where sanitizers lose it. Separating a delimiter's appearance from its identifier shows the identifier matters little against a bare task instruction, but carries most of a forged tool result and most of any forged turn once the system message tells the model to treat user content as data.

Rapid extraction of structured information from social media is important for humanitarian response, yet existing disaster tweet resources mainly provide document-level category labels without span-level entity annotations. We introduce HUMAID-NER, the first named entity recognition dataset built on the HumAID benchmark, containing 60,000 English disaster tweets annotated in BIO format across ten operationally motivated entity types and yielding approximately 175,000 labelled entity spans. Annotations are generated through a reproducible three-stage hybrid pipeline combining a spaCy transformer model, disaster-domain EntityRuler patterns, and structured regular expressions with priority-based overlap resolution. We also propose a joint multitask learning framework that performs disaster-specific named entity recognition and humanitarian event classification using a shared RoBERTa-large encoder. To reduce task conflict during joint training, the model uses homoscedastic uncertainty weighting with learnable task parameters and a two-stage training schedule that freezes the lower 18 of 24 encoder layers in the second stage. On the HUMAID-NER validation set, the proposed system achieves NER span micro-F1 of 0.841 and classification macro-F1 of 0.761 simultaneously. A real-time web dashboard demonstrates end-to-end deployment. The dataset, models, and pipeline code are released to support reproducibility and future crisis informatics research.

No-reference video quality assessment (NR VQA) has recently seen promising progress with deep learning. However, video data is inherently large, and processing them with deep models incurs high computational cost. This challenge is particularly acute in VQA, where preserving original-resolution cues and dense temporal information is critical for accuracy. Existing efficiency-driven preprocessing strategies, such as fragmenting, reduce computation but alter the input data distribution, limiting effective reuse of pretrained video foundation models (ViFMs). To address these challenges, we propose \textbf{H}igh-\textbf{F}idelity \textbf{V}ideo \textbf{Q}uality \textbf{A}ssessment (\textbf{HFVQA}), a framework built on fixed-size spatio-temporal (ST) patches that is fully compatible with pretrained ViFMs. HFVQA samples ST patches across multiple scales, including the original resolution, with minimal temporal subsampling to preserve low-level quality cues and semantic context. To limit computation, HFVQA introduces a lightweight auxiliary network trained end-to-end with the ViFM encoder to learn \textit{VQA-specific saliency}. Distilled directly from quality supervision, this saliency captures task-specific importance patterns, reflecting that video quality perception is dominated by a small subset of spatio-temporal regions. By combining high-fidelity spatio-temporal cues with learned, task-specific saliency, HFVQA achieves SOTA performance on standard NR VQA benchmarks while processing as little as 12\% of candidate ST patches, making high-fidelity ViFM-based VQA computationally tractable.

On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off between objective fidelity and optimization stability. Token-level OPD provides stable but local supervision, whereas sequence-level OPD captures future credit at the cost of horizon-dependent variance. We establish a unified temporal-credit view of these formulations, showing that practical token-level OPD can be interpreted as a temporal approximation to the sequence-level reverse-KL gradient. Building on this connection, we propose $γ$OPD, which uses discounted temporal credit assignment to balance long-horizon supervision and optimization stability, while admitting a horizon-independent variance bound. We further develop a reward-compatible bounded mixing (RBM) mechanism for $γ\mathrm{OPD}$ that balances verifiable outcome feedback with the discounted OPD advantage to move beyond purely teacher-dependent optimization. Experiments on mathematical and code reasoning demonstrate consistent improvements over existing OPD methods across vanilla, size-mismatched, and multi-teacher distillation settings.

Large language model (LLM)-powered coding agents have made rapid progress in automating software engineering tasks, yet repository-level issue resolution remains challenging. Beyond generating a plausible patch, an agent must localize relevant code across interdependent files and maintain repository context that is both sufficient and focused. Code graphs expose non-local relations, but linear text interfaces obscure their topology; rendering the full repository graph yields visual representations that are too dense to perceive reliably, whereas a one-shot local view becomes stale as exploration proceeds. We present \textbf{RepoAtlas}, a training-free module that maintains evolving multimodal repository views through a \emph{select--project--refresh} loop over a repository code graph. RepoAtlas combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget, projects the selected structure into complementary visual and textual representations, and refreshes the view when changes in the exploration state render it outdated. We evaluate RepoAtlas on SWE-bench Verified, where it improves the resolve rate by 2.4 points while reducing input tokens and model calls by 5.8\% and 7.8\% on average, relative to the strongest multimodal graph baseline, with consistent gains across three models of different families and scales.

Cranial implant generation is an important task in medical imaging. Recent point cloud based generative methods, particularly flow matching, offer strong reconstruction quality and efficient sampling, but still require multiple neural function evaluations during inference. This limits rapid generation of multiple plausible implant candidates. We propose Teacher-guided Endpoint Distillation (TED), a simple one-step distillation framework for conditional cranial implant generation on point clouds. TED trains a one-step student using teacher-guided endpoint supervision and geometric matching losses, while avoiding explicit path straightening. We evaluate TED on the SkullFix and SkullBreak benchmarks. TED achieves the best overall performance on the SkullBreak dataset, remains competitive on SkullFix, and provides the strongest Chamfer distance performance among the compared one-step methods. In addition, TED generates implants in approximately 0.04s per sample. These results show that one-step distillation can substantially accelerate conditional point cloud implant generation without sacrificing reconstruction quality.

We propose Low-Rank Quantile Surfaces (LRQS), a bivariate causal model in which, in the causal direction, an unknown monotone transformation of the conditional quantile surface admits a low-rank functional decomposition. LRQS subsumes location-scale noise models and post-nonlinear heteroscedastic noise models, while allowing multiple quantile bases to represent changes beyond location-scale effects. We prove generic identifiability of LRQS: the transformed quantile surface is low rank in the causal direction, whereas reverse representability under the corresponding constraints occurs only for exceptional, fine-tuned cause marginals. We provide a simple-yet-powerful causal score using a nonparametric fitting procedure that alternates between rank-constrained approximation of discretized quantile surfaces and isotonic estimation of the unknown monotone transformation. Experiments on synthetic mechanisms with higher-rank distributional shape variation and strong nonlinear distortions, together with standard bivariate benchmarks, show that LRQS is especially effective when conditional distributional shape or observation distortion goes beyond existing location-scale assumptions.

Hyperbolic geometry provides a natural inductive bias for genomic representation learning, but existing hyperbolic genomic models primarily use Lorentz convolutions to learn local sequence representations, while their residual pathways do not directly aggregate full Lorentz representations. We propose HyCoSeq, a contextual hyperbolic representation learning framework for genomic sequences. HyCoSeq incorporates weighted Lorentzian residual aggregation into multi-curvature Lorentz encoding, allowing full Lorentz representations to participate directly in geometry-consistent local aggregation. It further introduces a bidirectional long short-term memory network that integrates information from both sequence directions to learn contextual relationships among local representations at different positions within a genomic sequence, thereby extending local hyperbolic convolutional encoding to sequence-level contextualized representations. Extensive experiments across diverse genomic tasks show that HyCoSeq outperforms existing hyperbolic baselines and, without large-scale genomic pretraining, achieves competitive performance against substantially larger pretrained DNA language models.

This paper introduces NeuroSymbEAD, a large-scale neuro-symbolic caption dataset featuring an ego-centric knowledge graph (KG) of static and dynamic objects annotated with classes, categories, heading directions, orientations, and distances from the ego-vehicle. These annotations are used on the KITTI-360 dataset to generate multilevel textual captions representing a lightweight version of an ego-centric scene map. Outdoor scene-map reconstruction, visual recognition, and object grounding establish baselines for driving common sense and traffic/scene understanding. For these purposes, natural language-based grounded captioning of objects and their complex relationships is a widely adopted contextual representation for indoor scene tasks. Neuro-symbolic representations have proven effective in handling structured information for various computer vision and language applications. Our data annotation pipeline allows the generation of varied map segments, populating simulated or real objects within the bounding boxes predicted by any 3D object detection network, and building hierarchical text captions. We benchmark our neuro-symbolic and ontological caption generation using pre-trained grounding and learned auto-regressive captioning networks. By converting 3D driving scenes into structured ego-centric language, NeuroSymbEAD provides a benchmark for vision-language and foundation models for traffic-scene explanation, 3D reasoning, and interpretable autonomous-driving perception.

Multilayer Artificial Neural Networks trained via backpropagation are the basic blocks of many, more complex, classification algorithms. Their strength lies in the possibility of realizing, with arbitrary precision, any function. This result comes at the cost of the large number of involved parameters to be optimized. In this work, we propose a mechanism for cooperation, i.e., information exchange among several artificial neural networks, with the goal of reducing model complexity while maintaining performance. More precisely, we consider several "small" agents, i.e., containing fewer parameters than a reference "large" one, that during training share their predictions by incorporating this information into the loss function and thus directly influence weight updates. We consider several strategies for implementing cooperation, e.g., the voter model, majority model, and weighted average model based on an agent's confidence in its prediction. We numerically compare the accuracy of those strategies on several standard benchmarks. Our results support the claim that several small agents can outperform a single large model on a given classification task; the shared signals affect each agent's optimization algorithm by modulating both the descent direction and the step size, converging toward a global consensus. The proposed proof-of-concept significantly reduces the number of parameters to be trained while preserving comparable performance, thereby limiting computational resource usage.

We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems to retrieve relevant papers, identify supporting evidence, and generate answers. Lit3R combines off-the-shelf retrieval, reranking, and large language model (LLM) components without task-specific training. The retriever iteratively combines BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM-based verification, and complements retrieval based on the question with paper-to-paper expansion. The reader first identifies supporting evidence within individual papers and then synthesizes evidence across papers to produce the final answer and evidence trace. On the official test set, our system ranked 4th on the leaderboard. Our code is available at https://github.com/tus-ist-nlp/littraceqa.

Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with pornography, fraud, gambling, or illicit transactions. Existing benchmarks evaluate obfuscated text and risky webpages separately, obscuring how target recovery affects downstream evidence acquisition. We introduce RiskChainBench, pairing 3,600 synthetic token-text restoration inputs from 600 source sessions with 600 corresponding human-labeled local web environments. A model first restores the message, operational intent, and destination; the same underlying model then acts as a VLM-driven web agent that investigates the correctly associated website and produces a frozen, evidence-cited risk report without message-side semantics or domain-reputation cues. We score restoration and correct-routing web investigation separately and compose them offline by applying the frozen primary-entry prediction as a gate to the same Task 2 result. Human labels determine task correctness, while a fixed multimodal evidence judge assesses faithfulness, sufficiency, completeness, and consistency. Across ten models, Entry Top-1 ranges from 35.2% to 95.2% and web decision accuracy from 26.3% to 62.8%; the leading systems differ across entry recovery, full reconstruction, website decisions, and fine-grained typing. Execution failures account for 31.9% of web runs, whereas post-decision type errors account for only 0.9%, identifying stable exploration and risk judgment as the principal bottlenecks. We release the benchmark, protocol, and resettable local sandbox.

Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-of-magnitude speedup for individual HE operations. However, when directly applying a commercial HE accelerator to state-of-the-art HE-MPC frameworks, we observe only limited end-to-end performance gain. This is because HE-MPC frameworks often require wireless transmission of input and output ciphertexts for each HE operation, leading to a severe network communication bottleneck. To overcome this challenge, we introduce OptiPrime, a protocol-hardware co-optimization framework for efficient private DNN inference. OptiPrime features a novel HE protocol for convolutions that substantially reduces the number of transmitted output ciphertexts and mitigates the network communication bottleneck. Meanwhile, as the new protocol introduces complex computation for fewer output ciphertext, we observe new memory access challenges due to a high volume of weight plaintexts and intermediate ciphertexts. Hence, we further propose a lightweight compression system for the weight plaintexts, reducing memory traffic by 10 times, as well as a specialized dataflow to maximize on-chip data reuse of intermediate ciphertexts. Extensive experiments show that our framework outperforms the Cheetah baseline by at most 5.7 times on CPUs and 4.2 times with an accelerator.

Long-horizon reasoning is vulnerable to early errors that compromise later decisions. We present QART, the Quantum-Augmented Reasoning Transformer, a quantum--classical hybrid architecture combining a backbone language model with quantum encoding, CIM-based QUBO optimization, and quantum decoding. Semantic information can come from hidden representations or model-generated text; detailed encoding and optimization procedures remain proprietary. Under explicit assumptions, we establish a conditional asymptotic reliability separation from single-trajectory autoregressive LLMs. For a common task family with aligned optimality and acceptance criteria, autoregressive acceptance probability tends to zero when cumulative conditional risk of irreversible errors diverges. QART's task-optimal-path recovery probability remains bounded away from zero if conditional probabilities for optimal-path coverage and semantic fidelity, spectral certification, dynamical reachability, and faithful readout remain uniformly positive under a specified resource schedule. The architecture alone does not imply these bounds. Paired measurements on six long-horizon benchmarks using DeepSeek V4 Flash, GLM-5.3, and GPT-5.5 xhigh in a Codex agent environment favor QART in 14 of 15 backbone--benchmark pairs. Relative gains reach 84.0% on SciCode, 47.6% on $τ^3$-Bench, and 44.4% on Terminal-Bench 4.0; the DeepSeek V4 Flash configuration regresses by 7.8% on DeepSWE. These results do not directly validate the asymptotic separation. Potential quantum scaling laws are formulated as conditional hypotheses. A quantum-advantage interpretation requires a demonstrated CIM quantum advantage over strong classical solvers and its transfer to end-to-end reasoning after all system overheads.

Space robots are increasingly expected to perform long-duration, contact-rich, and multi-stage operations with limited human intervention. Recent advances in artificial intelligence (AI), robot learning, and embodied foundation models provide new opportunities to improve the autonomy and adaptability of such systems, but their transfer to space is constrained by scarce mission data, space-specific dynamics and sensing conditions, limited onboard resources, and stringent safety requirements. This article reviews artificial intelligence-enabled space robot operations (AI-SRO) from a capability-building perspective. We first summarize representative operational scenarios, autonomy trends, and space-specific constraints. We then establish a three-layer technical framework comprising capability foundations, capability formation, and capability deployment/evolution. Within this framework, we review simulation environments, datasets and benchmarks; task and environment understanding, state perception, decision-making and planning, and action execution; and onboard deployment, ground-to-space adaptation, continual learning, and capability transfer. Finally, we propose key research directions toward trustworthy simulation and data, open-world multimodal cognition, long-horizon safe decision-making, physically constrained policy learning, and space computing infrastructures.

Despite its crucial role in video object removal (VOR), existing evaluation paradigms face two critical limitations: questionable references and a misalignment between tradi- tional metrics and human preference. To address these challenges, we introduce VOR- Bench, which advances VOR evaluation through three integrated components. First, we present the VOR Dataset (VORD), the first benchmark dataset providing both paired edited videos and graffiti masks. Its unique strength lies in a diverse data spectrum, which encompasses model-generated, tool-rendered, and camera-captured data, ensuring robust assessment across real-world scenarios. Second, we develop rMPAF, a realistic Motion- capable Paired-video Acquisition Framework. By combining the strengths of image- based object removal and fine-tuned video generation models, rMPAF automatically generates realistic, motion-coherent paired videos. Finally, we propose three evaluation dimensions and introduce VOR-MDSM, the first perception-driven VLM-based scoring model specifically designed for mask-guided VOR. It bridges the gap between arithmetic metrics and human perception by covering the essential visual attributes and matching nuanced human judgment. Extensive experiments demonstrate that VOR-Bench yields evaluation results that align closely with human perception, achieving a remarkable cor- relation (\r{ho} > 0.9) with subjective assessments. We will release VOR-Bench along with its documentation to ensure full reproducibility.

Upgrading embedding models typically requires expensive database re-indexing, as new query embeddings are incompatible with existing database embeddings. While Backward Compatible Training (BCT) mitigates this by enforcing compatibility during training, existing approaches often require updating the backbone model. This is impractical because of significant training cost, the risk of performance regression, and limited access to proprietary model weights. We introduce Multi-modal Knowledge Preserving Adapter (MKP-Adapter), the first adapter-only BCT approach for Multi-modal Large Language Models (MLLMs) that requires no backbone updates. We identified that the primary challenge in adapter-only BCT is preserving the knowledge of the new embeddings while enforcing backward compatibility. Hence, we propose a multi-level preservation loss that maintains the geometric structure of the embedding spaces throughout BCT. Furthermore, a focal re-weighting strategy is integrated to prioritize learning from challenging samples. Experiments demonstrate that our method achieves strong backward compatibility across diverse multi-modal benchmarks (image, text, visual document, and video retrieval tasks) and model types. Notably, MKP-Adapter is trained solely on pre-extracted embeddings and requires only negligible additional latency relative to the original backbone forward pass, highlighting its efficiency.

Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the execution cost. Despite its practical impact, prediction decoding has received comparatively little attention and is often implemented using generic CPU routines or inefficient GPU kernels, limiting the benefits of advances in model efficiency. In this work, we investigate the decoding overhead associated with a recent sinusoidal centroid encoding for Instance Segmentation, in which each pixel regresses a positional embedding of its instance centroid. This approach allows flexible segmentation without predefined proposals, but extracting instance masks from dense embeddings incurs a high computational cost. We present an optimized CUDA-based implementation of the decoding algorithm tailored to this encoding, explicitly addressing challenges related to parallelization, synchronization, and memory access on modern GPUs. Our solution significantly reduces decoding overhead and improves End-to-End inference latency, outperforming both CPU-based approaches and naive GPU implementations. The results demonstrate that efficient decoding is essential to fully exploit the advantages of advanced output representations and highlight the importance of jointly designing encoding schemes and their decoding algorithms for real-time computer vision systems.

Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks because they operate on a single observation at inference time. We identify two representational failures that underlie this limitation. The first is motion ambiguity, where a single observation does not include scene dynamics and therefore cannot anticipate the future state of moving objects. The second is state aliasing, where visually similar observations from different points in a task require different actions. We argue that these failures persist regardless of model scale and inference latency, showing that the bottleneck is missing temporal context rather than model capacity. Based on this insight, we propose TEMPO, which augments a pretrained VLA with two temporal inputs: a motion summary extracted from a frozen video foundation model to resolve motion ambiguity and a compact proprioceptive history to resolve state aliasing. TEMPO requires no modification to the backbone and adds minimal compute overhead at training or deployment. Across four dynamic manipulation tasks, it improves Bottle Handover success from 44% to 74% and is the only method that solves state aliasing. Probing and ablation studies confirm that each temporal signal independently addresses its corresponding failure. We further release TEMPO-Bench, a benchmark of over 50k annotated frames for evaluating motion-aware robot perception in both regression and multiple-choice formats. Project Website: https://tempo-robot.github.io/

To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manually. For a script that can be read by only a small number of specialists, this manual transcription is a limitation, because the trained models are supposed to save the time of those same specialists. A relevant question therefore arises: how many transcriptions are needed before a recogniser becomes useful, and how much of that cost can pretraining remove? In this study the answer is measured directly for handwritten Devanagari. We keep the recogniser, optimiser and evaluation protocol the same and change only the number of real transcribed words used for fine-tuning across nine budgets from 10 to 4,000 and four initialisation regimes, with six seeds at every point. The resulting curves are then converted into annotation-equivalent terms. A CER of 0.50 is reached by supervised synthetic pretraining using only 81 transcribed words, whereas random initialisation requires 355, which gives a label multiplier of 4.40 [3.56, 4.99]. There is a zero-shot reference point as well: with no real transcribed words at all, this pretraining is worth about 136 of them. This advantage gets smaller as the target accuracy improves, and at the most demanding target we measure, it cannot be distinguished from no saving at all. A fourth arm in which only the encoder is transferred separates the effect of the pretraining method from that of transfer scope, and masked image modelling is observed to transfer negatively over a bounded range of budgets. We emphasise that the scarcity in this study is constructed by subsampling a large corpus.

Industrial IoT environments increasingly deploy autonomous mobile robots for tasks such as material handling, product assembly, or infrastructure inspection. In such deployments, collaborative perception enables robots to share LiDAR observations and collectively construct a richer model of their environment than an individual agent could produce alone. However, industrial environments are dynamic spaces where robot positions shift continuously, network bandwidth fluctuates, and the marginal contribution of robots to perception quality varies at runtime. Existing collaborative perception approaches are designed for static participation assumptions and cannot adapt to these dynamics without sacrificing either detection precision or communication efficiency. This paper presents CoAdapt, an adaptive collaborative perception framework for IIoT robotic swarms in which a Large Language Model (LLM) serves as a runtime fusion controller, jointly deciding which robots participate in the fusion process and which fusion algorithm to apply based on the current spatial configuration and network state. The LLM reasons over structured natural language descriptions of the scene derived from raw LiDAR point clouds, requiring no taskspecific training and generalizing to unseen swarm topologies. Evaluated on the OPV2V benchmark across 25 scenarios, our approach achieves a 38% reduction in communication cost while maintaining detection precision comparable to static baseline approaches.

Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance. At its core, RegRet integrates a Region-Aware Encoder to capture detailed regional features while balancing them with the global background context. To further enhance the fine-grained understanding and discriminability of representations, we design a multi-stage training pipeline that includes detailed localized captioning and regional contrastive learning tasks. In addition, considering the absence of region-level contrastive training data and the limited diversity of evaluation tasks in current benchmarks, we introduce the REGMB benchmark. It comprises 225k contrastive pairs, covering four multimodal retrieval tasks. Extensive experiments validate the effectiveness of our approach. RegRet outperforms strong baselines in the zero-shot setting. Further training with contrastive learning leads to an average improvement of more than 20\% on both REGMB and public benchmarks, while achieving comparable or better results on global-level retrieval tasks.

Facial Landmark Detection(FLD) is a crucial task in various applications and has achieved significant advancements in recent years. However, current FLD methods still struggle under challenging conditions, where facial structural variations, information loss, and noise interference severely compromise the integrity and accuracy of learned facial features. To address these issues, we propose Frequency-Adaptive Heatmap-Conditional Diffusion Network (FAHCD-Net), which integrates a Frequency-Adaptive Heatmap-Conditional Diffusion (FAHCD) model with a Smoothness Regularization (SR) loss in a cascaded framework. Specifically, the FAHCD model incorporates a Hierarchical Frequency Adaptation (HFA) module designed to suppress redundant high-frequency noise through multi-layer frequency decomposition and adaptive reconstruction, thereby preserving essential facial structures. Additionally, the SR loss is proposed to further mitigate the interference of high-frequency noise and enhance the smoothness of the generated landmark heatmaps. By cascading the FAHCD model with the SR loss, FAHCD-Net effectively leverages both statistical and frequency-based distribution characteristics of the data to progressively generate more accurate landmark heatmaps from noisy inputs. Extensive experiments on popular benchmarks demonstrate the effectiveness and robustness of the proposed method, achieving state-of-the-art performance in FLD tasks under challenging scenarios. The source code is available at https://github.com/HJWKryptonite/FAHCD-Net.

Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost. To reduce this overhead without retraining, existing methods select compact token subsets that prioritize query relevance, visual coverage, or a fixed trade-off between them. The appropriate balance, however, varies across queries and token budgets: localized questions favor relevance, whereas holistic questions demand broader visual coverage. We introduce StackTok, a training-free selector that treats query relevance as the objective and visual coverage as budget-calibrated support. StackTok builds a size-indexed coverage reference from a coverage-only greedy sequence and adjusts its support target using query--vision affinity entropy. A reference-gated interleaved selection policy then switches between relevance- and coverage-oriented additions according to the current subset's support deficit. For high-resolution inputs, StackTok allocates one shared token budget across crops according to the combined marginal gain of locally nominated tokens. Evaluated with five VLMs over ten distinct image-understanding benchmarks, StackTok ranks first among training-free selectors in every tested model--budget setting. On high-resolution LLaVA-NeXT-7B, it retains 95.26% of full-token performance with only 160 of 2{,}880 (5.6%) visual tokens.

Local image watermarking embeds an invisible signal into selected image regions rather than spreading it across the entire image, enabling payload recovery from specific objects or regions without perceptibly altering the image. Existing studies evaluate the robustness of payload recovery and localization under image transformations, but they often focus on their own proposed method, resulting in narrow evaluations with inconsistent choices of transformations, datasets, and metrics. These inconsistencies across studies limit direct comparisons across methods and muddle the overall picture of local watermark robustness. To address this gap, we present the first systematic robustness benchmark for local watermarks across 55 image transformations, including (i) signal distortions, (ii) changes in image coordinate alignment, (iii) indirect local edits, and (iv) direct watermark edits. The benchmark evaluates MaskWM, WAM, OmniGuard, TrustMark, and PixelSeal, all methods that either provide native localization or require minimal adaptation to support it. Our results show that all evaluated methods are vulnerable to some transformation, with MaskWM standing out as offering the strongest payload recovery and localization, although it has the lowest image quality in the clean setting. Synchronization further improves MaskWM's payload recovery under several geometric transformations, albeit at an additional cost to image quality. A key finding is that local watermark robustness depends strongly on the nature of the transformation: signal distortions are often tolerated by the strongest methods, while geometric misalignment and generative local edits, such as inpainting and outpainting, can completely impair payload recovery. We observe that payload recovery and localization are related but not interchangeable, and both strongly depend on the transformation's impact on the watermark region.

High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit exceptional storage capabilities and robustness. Previous empirical studies identified a hyperparameter regime, the "Ridge of Optimization," where attractor stability is maximized. However, the geometric nature of this regime and the optimization dynamics required to reach it have remained unclear. In this paper, we investigate the static geometry of the parameter space and the learning trajectory of Gradient Descent (GD) in KLR-trained Hopfield networks. Using the eigenvalue spectrum of the Hessian, we reveal that the Ridge corresponds to a phase boundary located adjacent to a rank-1 spectral collapse, acting as a geometric singularity where the principal curvature is massively amplified. Furthermore, we demonstrate that the learning dynamics exhibit a transient self-stabilizing behavior driven by the Edge of Stability (EoS) phenomenon. Rather than seeking flat regions, the network parameters are driven toward a state where the local curvature dynamically equilibrates near the stability limit dictated by the learning rate, allowing the optimization to survive the initial instability. We provide analytical derivations for both the rank-1 asymptotic collapse and the dynamic feedback loop governing this equilibration. These findings suggest that optimal, high-capacity memory representations are not formed in flat minima, but are dynamically sculpted at the highly curved boundaries of geometric singularities.

Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays the same. These local changes may cancel when rewards are averaged across agents, so the number of local changes $\Stloc$ can be much larger than the number of changes in the best common arm $\Stdec$. We introduce Decision-Relevant Fresh Comparison (DRFC), which uses new, balanced samples from all agents to compare arms at the network level and switches only when fresh global evidence indicates that the common best arm has changed. We prove a high-probability dynamic regret bound with no adaptation term depending on $\Stloc$, and show that every algorithm must still pay for identifying genuine decision switches and propagating them through the communication graph. Under a distinct time-average benchmark, an anytime-valid sliding-window extension handles gradual drift; experiments on synthetic, semi-real, and MovieLens-1M replays show that DRFC ignores decision-irrelevant local changes while the extension avoids false switches.

Photonic neural networks (PNNs) offer efficient analog inference, but parameters optimized under ideal device models can degrade after fabrication, creating a persistent simulation-to-hardware (sim-to-real) gap. When many identically designed chips are deployed, calibrating each device from scratch compounds this cost. We propose Latent Chip Adaptation from Probes (LCAP), a population-informed framework that decomposes hardware adaptation into a transferable population correction and probe-inferred latent personalization. LCAP first learns a shared correction from 80 historical chips, then extracts a low-dimensional correction space from device-specific refinements. At deployment, 32 fixed unlabeled output probes infer an unseen chip's latent correction coordinates, enabling feed-forward personalization without target-device optimization. On a three-layer 64-mode MZI simulator with phase variation, beam-splitter errors, quantization, and crosstalk, accuracy improves from 80.4147% under direct deployment to 92.6860% after shared calibration and 93.3617% with LCAP. LCAP improves 27/30 unseen chips and raises worst-device accuracy from 89.18% to 90.54%.

This study covers foundational concepts for enhancing plan-execution flexibility, including partial-order planning, the producer-consumer-threat formalism, and a range of deordering and reordering strategies. Creating a partial-order plan from a sequential one by removing unnecessary ordering constraints is a practical way to improve execution flexibility, and several methods have been proposed for this task. This study analyzes their capabilities across ordering, action handling, parameter handling, plan structure, concurrency, and complexity, and evaluates them against each other on a shared benchmark. The central finding is that block deordering-based approaches, which restructure causal dependencies through block-level grouping and subplan substitution, substantially outperform MaxSAT-based approaches despite the latter's theoretical guarantees of minimum reordering. The reason is structural: minimum reordering optimizes within the causal structure already present in the plan, whereas block deordering-based methods change that structure, exposing orderings that would otherwise appear necessary. A further distinction is practical: block deordering-based methods are anytime algorithms that always return a valid result, while MaxSAT-based methods fail entirely on a substantial portion of plans and offer no partial solution when they do. Block substitution further extends the parallel execution by formalizing non-concurrency constraints, though its impact is limited to domains with resource-based interactions. On efficiency, block deordering-based approaches achieve the highest flex gain per unit of computation time, while MaxSAT-based encodings incur large computational overhead.

Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and automated grading. Such rubrics are reliable only if they reward honest answers over adversarial answers optimized to exploit them. Yet their robustness to such optimization remains poorly understood. We isolate the hardest regime: impossible tasks, where the prompt pressures the model toward an unsupported conclusion, so the only honest response is to acknowledge the impossibility. We introduce ImpossibleRubrics, a benchmark of 169 impossible tasks spanning six impossibility categories, each paired with a verifiable oracle certificate specifying what an honest answer may and may not claim, together with 48 answerable controls. Rather than providing fixed rubrics, ImpossibleRubrics provides task environments and certificates, allowing rubrics to be generated downstream and then adversarially tested for whether they reward certificate-violating answers. Eleven generators are exploited 8--26% of the time on the unbiased 150-of-169 environment cut; on a deliberately selected stress cut the strongest generator we measured is still exploited 36% while a certificate-faithful rubric is exploited 0%, so what we measure is a rubric-quality gap, not task impossibility. One result runs against intuition. A single generic rubric ("be decisive, penalize hedging") used unchanged for every task is exploited 64% of the time, and seven of the eleven generators are exploited more often than that while writing a rubric tailored to each one. The tailored criteria appear to tell an attacker which claim to fabricate. The problem is not that rubrics are vague; it is that they are specific about the wrong things.

Visuomotor policies observe both the task scene and the acting embodiment, allowing embodiment-specific visual cues to influence action prediction. We study this phenomenon as visual embodiment dependence (VED) and show, through cue-conflict interventions across representative policies, that visible robot configuration can become a shortcut to task progress. Rather than eliminating VED, we argue that it should be structured around embodiment information that supports control and generalization. We realize this through embodiment canonicalization in 3D point clouds, replacing the original embodiment with a canonical end-effector representation (CER) that preserves control-relevant geometry while abstracting embodiment-specific morphology. Its editable form further enables configuration-decorrelation augmentation for unfamiliar robot configurations. Experiments show that embodiment canonicalization substantially improves human-to-robot policy transfer without robot demonstrations, while simply removing the embodiment is insufficient without preserving control-relevant geometry. We further find that CER itself can become a configuration shortcut when robot configuration becomes decoupled from task progress; configuration-decorrelation augmentation mitigates this failure mode and restores robust recovery without sacrificing performance on seen configurations. Together, these results show that robust visuomotor learning benefits from structuring, rather than removing, visual embodiment information. Project website: https://tonyfang.net/ved

Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity of large-scale annotated event data. Pretrained image models provide scalable semantic supervision, but existing image-to-event methods rely on rigid pixel-wise or token-wise alignment that overlooks modality discrepancies in texture, density, and appearance, potentially causing semantic collapse and limiting transferability. To address this issue, we propose Hyper-RED, a simple, painless, and scalable image-to-event pretraining framework that transfers high-order semantic structures from images to events. Hyper-RED uses hypergraphs to model and align high-order semantic associations among multiple image and event tokens, enabling cross-modal knowledge transfer while accommodating modality-specific differences rather than enforcing rigid one-to-one correspondence. Specifically, given a paired event--image sample, Hyper-RED leverages DINOv3 to extract spatial token representations and constructs image, event, and cross-modal semantic hypergraphs, where each hyperedge connects multiple semantically correlated tokens. We further introduce a hypergraph relational distillation loss that imposes complementary intra- and cross-modal constraints, enabling the event encoder to inherit image-derived semantic organization while preserving local relational consistency and event-specific characteristics. Experiments on three tasks across five event datasets demonstrate consistent scaling from ViT-S to ViT-L and state-of-the-art performance (Fig.1). The code is available at: https://github.com/meisenwang/Hyper--RED.

Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with wearable physiological signals, which are multichannel, irregularly sampled, noisy, and governed by coupled continuous-time dynamics spanning distinct spectral scales. We present SOTER, a generative foundation model for wearable physiological time series that unifies cross-channel coupling, spectrum-guided expert specialization, and continuous-time latent evolution within a single pre-training framework. SOTER combines a spatial feature-aware backbone that models inter-signal dependencies, a power spectral density (PSD)-guided mixture-of-experts layer that routes representations to experts associated with fixed spectral bands through an inspectable, non-learned rule, and a neural controlled differential equation decoder that supports prediction and imputation at arbitrary timestamps. We pre-train SOTER on 226 billion time points from five public physiological datasets and evaluate the same pre-trained model across out-of-distribution zero-shot forecasting, frozen-encoder linear-probe classification, and continuous-time imputation on wearable benchmarks. SOTER achieves the best RMSE on 4 of 6 datasets and the best MAE on 5 of 6 in zero-shot forecasting, the highest average Macro-AUROC in classification, and the lowest imputation error on all six datasets at 75% missingness. It further remains robust to additive acquisition noise, matching or surpassing baselines evaluated on clean inputs even under the strongest corruption. These results indicate that domain-specialized foundation models for wearable physiology benefit from jointly modeling channel structure, spectral scale, and continuous-time dynamics.

Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remains a key challenge. Existing memory-augmented approaches retrieve individual past examples as direct references, but do not explicitly synthesize actionable strategies from them, causing the same types of errors to recur. We propose Dynamic Retrieval-based Policy Generation (DRPG), a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement. We evaluate DRPG across six benchmarks spanning text-to-SQL, question answering, medical diagnosis, and Python programming, using seven LLMs from both proprietary and open-weight families. DRPG outperforms strong baselines across most datasets and models. Further analysis demonstrates that DRPG's policy generation is robust to retrieval strategy, operates effectively without prior policy continuity, and can leverage smaller or cross-family models as cost-efficient policy generators. We also find that the benefit of policy-level guidance depends on task characteristics, offering practical insights into when and under what conditions this mechanism is most effective.

Query-based segmentation methods have shown promising potential for surgical instrument segmentation and recognition, which is essential for scene understanding and downstream tasks in computer assisted surgery. However, most existing approaches predominantly rely on per-frame predictions and overlook cross-frame temporal priors as well as temporal-consistency constraints. This limitation often leads to unstable query representations and suboptimal category recognition. In this paper, we propose TEDi, a Temporal memory-Enhanced and Denoising transformer for surgical instrument segmentation that addresses these is sues through Memory Search Enhancement and Temporal Consistency Denoising. The former introduces a query-level memory bank and a memory search enhancement encoder to retrieve discriminative representations from historical frames, enriching current-frame features. The latter constructs a temporally consistent reference as a cross-frame semantic anchor to suppress temporally unstable predictions and promote semantic coherence across frames. Extensive experiments on two benchmark datasets, EndoVis 2017 and EndoVis 2018, demonstrate that TEDi consistently outperforms state-of-the-art methods, highlighting its potential to further advance computer-assisted surgery. Our code is available at github.com/argon-xixi/TEDi.

Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved from external sources. However, MLLMs may overlook relevant evidence in both modalities, attending weakly to the textual sentences or visual regions needed for the correct answer. Recent efforts address this by highlighting retrieved text and marking visual regions before generation, but apply a fixed, one-shot policy that cannot adapt to three sources of variation: whether highlighting is necessary, how much evidence different examples require, and when different textual evidence becomes relevant as the answer unfolds. We introduce Adaptive Relevance-guided Evidence Allocation (AREA), a training-free inference-time method that formulates evidence highlighting as adaptive allocation. AREA generates a single probe token to read visual and textual relevance from fixed backbone layers, then makes three decisions: i) whether to intervene (controlled by natural attention coverage and visual sink contamination), ii) how much evidence to expose (determined by relevance entropy), and iii) when to refresh text during generation (triggered by causal context-attention peaks). Across four KB-VQA and seven standard multimodal benchmarks with nine frozen MLLM checkpoints, establishes the best performance among training-free highlighting methods.

Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectures about why the L1 loss outperforms L2 here. First, the hypothesis that the L1 loss confers robustness via parameter sparsity confuses the loss with Lasso regularization: an explicit Lasso penalty produces the predicted sparsity yet fails to reproduce L1's cross-noise behavior, while L1- and L2-trained weight distributions are indistinguishable. Second, the population optima of the two losses coincide exactly for symmetric signal posteriors and nearly so for concentrated ones. Measured differences are therefore dominated by optimization dynamics (bounded-influence gradients), which we probe with gradient statistics and contaminated-target training. On Kodak24 with five synthetic noise families, the L1 loss holds a statistically significant edge over L2, below 1 dB PSNR, holding across three seeds on 13 of the 14 noise columns. On real camera noise the loss is not the decisive variable in distribution: on official SIDD validation blocks, synthetic-Gaussian-trained N2N models gain only 0.8 to 3.7 dB over the noisy input regardless of loss, while retraining on SIDD's own noisy pairs, never reading ground truth, gains 9.4 to 11.0 dB, far ahead of BM3D. All metrics are on raw network outputs, and the study makes no leaderboard claim. The training pair distribution, not the loss, carries the inductive bias. That design rule applies wherever clean references are unobtainable, from microscopy to industrial inspection sensors.

In this work, we propose a structured methodology for the system identification of underwater vehicles through the design of optimal excitation trajectories. To this end, the trajectories are parameterized using Bezier curves, which ensure smooth and differentiable motion profiles while facilitating the enforcement of constraints through appropriate manipulation of the control points. An optimization problem is formulated to determine a dynamically feasible excitation trajectory that respects safety limits and maximizes the quality of the collected data, thereby enabling reliable estimation of the vehicle's dynamic parameters using least squares. The proposed methodology is experimentally validated in a laboratory water tank, where the dynamic parameters, identified from the optimized trajectory, are evaluated by predicting the vehicle's velocity through forward simulation on previously unseen trajectories.

LLMs are increasingly employed in a wide range of decision-making tasks. However, the opacity of their internal reasoning makes it difficult to validate or interpret their outputs, and the need for interpretability becomes especially critical in high-stakes settings. This study examines the decision-making capabilities of LLMs through the Analytic Hierarchy Process (AHP), a classical and widely used multicriteria decision-making framework. We construct a new annotated benchmark based on AHP and propose the first end-to-end approach that enables LLMs to perform the complete AHP workflow. Experiments in real-world decision problems in the legal and higher-education ranking domains show that our method significantly improves alignment with expert judgments.

The unchecked proliferation of manipulated images on social media platforms has increased the spread of misinformation, posing a severe threat to public trust and information integrity. Modern deepfake detectors typically rely on Vision Transformers (ViTs) to capture the low-level inconsistencies that characterize fully synthetic or locally tampered images. However, the global understanding of such foundation models is not enough to discriminate alone between real and fake multimedia content, especially in challenging scenarios where images are compressed or transmitted through social media. In this paper we pioneer the application of Joint-Embedding Predictive Architecture (JEPA) models to deepfake detection, taking advantage of the generalized representation of visual reality that such World Models have exhibited. We hypothesize, and empirically demonstrate, that the intrinsic world understanding of JEPA models can be used as a strong prior for a deepfake detector. To fully exploit JEPA capabilities, we propose MoE-JEPA, a dual-stream architecture for deepfake detection. By enhancing a V-JEPA 2 backbone with a Residual Mixture-of-Experts (MoE) mechanism, along with a noise stream branch, our model dynamically internalizes forensic knowledge. Furthermore, a Gated Attention Multiple Instance Learning (MIL) module is employed to ensure precise spatial semantic understanding. Evaluated on the SID-Set benchmark, comprising 300K AI-generated, tampered and authentic images, MoE-JEPA establishes a new state-of-the-art with an accuracy of 95.54%, successfully outperforming vastly larger models.

As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against \textit{persuasion attacks}---attempts to inject misinformation or enforce counterfactuals---has become a critical safety concern. Existing red-teaming frameworks typically evaluate models in multi-turn dialogues where the target model retains full conversation history. We identify a critical flaw in this setting termed \textbf{``Refusal Inertia''}: a model's initial refusal often propagates through subsequent turns largely to maintain contextual consistency, thereby masking its true vulnerability to sophisticated, isolated persuasion attempts. To rigorously evaluate the ``cold-start'' defense capabilities of SOTA models, we introduce the \textbf{SAST-IR} (Stateful Attacker, Stateless Target - Iterative Refinement) framework. By enforcing a memory wipe on the target while retaining the attacker's history, we simulate a worst-case adversarial setting using \textbf{multi-turn} (stateless) iterations. Leveraging \textbf{CP-Agent} (Cognitive Persuasion Agent), an enhanced diagnosis-guided agent, our experiments on the custom \textsc{CounterFact-Strict} dataset ($N=50$) yield alarming results: simple, diverse attack strategies achieved a staggering \textbf{96\%} success rate, exposing severe brittleness in memory-less defense. Furthermore, we reveal a \textbf{``Complexity Paradox''}: while complex, iteratively refined attacks are effective, they often trigger defensive compliance, whereas simple strategies achieve a higher rate of genuine persuasion (\textbf{84.7\%}). Our code and dataset are available at GitHub, https://github.com/cza1006/llm-persuasion-defense.

Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods reduce this effort but stay interaction-inefficient: slice-wise methods (including many foundation models) ignore inter-slice continuity, while 3D and video-based methods propagate a prompt with a \emph{fixed} propagator that never adapts to the target volume, so it drifts on low-contrast or pathological structures and must be re-prompted. We present IMVS, a human-in-the-loop annotation framework that composes three components into a closed loop rather than a new segmentation primitive: a lightweight 2D Slice Mask Adapter (SMA) fine-tuned online from user scribbles, a frozen Volume Mask Tracker (VMT) that propagates corrected masks across adjacent slices, and a soft teacher--student alignment that limits forgetting. The SMA is backbone-agnostic (UNet++, DeepLabV3, TransUNet). Across 8 public CT/MRI datasets, IMVS matches strong interactive baselines in quality while sharply cutting annotation effort: $14.4\times$ faster than a proficient copy-based manual workflow ($22.3\times$ over naive manual), $4.6\times$ over slice-wise and $1.9\times$ over 3D interactive methods. MedSAM2 and ScribblePrompt stay competitive or stronger on well-delineated organs; IMVS's advantage is largest on challenging targets and on interaction efficiency. Source code and Demo Video: https://github.com/AbhilakshSinghReen/imvs.

Post-disaster phasor measurement unit (PMU) outages reduce power-system observability and degrade operator situational awareness, requiring sequential restoration under limited resources. Existing PMU restoration methods based on optimization or heuristics can generate restoration schedules, but they often provide limited support for explanation, traceability, and operator interaction. This paper proposes an agentic tool-calling framework orchestrated by a large language model (LLM) for post-disaster PMU restoration and grid observability recovery. In this framework, the LLM does not directly solve the restoration optimization problem; instead, it coordinates validated backend tools required for post-disaster restoration, including observability assessment, restoration planning, state updates, and operator verification. The framework also maintains a structured tool-call history and execution context that keep restoration decisions traceable and explainable, while enabling context-aware operator question answering during the restoration process. Simulation results on IEEE 30-bus and IEEE 57-bus systems show that the proposed framework achieves observability recovery comparable to a mixed-integer linear programming (MILP) solution, while providing tool-grounded explanations, interactive operator support, and human-overseen execution.

Image segmentation remains challenging due to occlusions, poor lighting, and irregular structures. Although transformer-based methods achieve high accuracy, they rely heavily on long-range spatial features, leading to high computational costs and neglecting prior knowledge or noise patterns, resulting in missing details and unclear boundaries. To address these issues, we propose Frequency Spatial Aware Network (FSANet), which integrates prior knowledge with a dual-domain solver to sequentially adapt to diverse segmentation tasks. Specifically, we design three key modules: (1) Structure Prior Module, which recovers overlooked details; (2) Dual-Domain Awareness Module, which captures salient features while disentangling noise; and (3) Edge Estimation Module, which enhances edge awareness for more precise segmentation. In addition, the limited availability of comprehensive segmentation datasets covering various real-world scenarios hinders the performance of existing methods. To address this, we introduce SceneX, a novel open-source dataset featuring 10 challenging non-ideal scenarios, establishing a new benchmark for evaluating and improving the robustness and real-world applicability of the segmentation models. Extensive experiments demonstrate the efficiency and effectiveness of FSANet.

IMU-based human activity recognition (HAR) enables continuous, privacy-friendly monitoring of daily activities using wearable sensors. However, building reliable HAR models that generalize across diverse users and real-world conditions requires large amounts of labeled IMU data, which are expensive and difficult to collect. Existing approaches mainly rely on augmentation or synthesis to expand available data, but indiscriminately adding virtual samples may provide little new coverage and introduce unreliable supervision. To overcome these challenges, we propose a novel coverage-aware virtual IMU augmentation framework that decides where to supplement real data, how to generate and select virtual candidates, and how strongly to weight them during training. Specifically, we select diversity and scarcity anchors in a learned sensor embedding space, convert anchor dynamics into prompts, and generate virtual IMU candidates for each anchor. We then rank candidates by a selection cost combining anchor proximity and label consistency, and incorporate the selected candidates into HAR training with reliability-based weights. Experiments on public HAR benchmarks show that our method consistently improves recognition performance over competitive baselines, and ablation studies confirm the effectiveness of the proposed framework design.

With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, especially involving multi-step thinking or interaction with tools. For applying LLM techniques with a well-designed agent paradigm, post-training of LLM in multiple agent scenarios is necessary to achieve better performance. Among the variable post-training techniques, alignment methods such as PPO, DPO, DIL, and GRPO become popular because many papers show a significant positive impact on the model's performance by punishing negative samples while keeping acceptable training complexity. However, most alignment methods address simple single-turn tasks, and there remains room for improvement for complex multi-turn tasks. We propose Turn-level Multiscale Density Ratio Estimation (tlm-DRE), which assigns different weights on corresponding turns and proposes asymmetric token-level training based on the positive-negative space gaps across multiple turns of tasks. The results of the experiment on a wide range of agent benchmarks show that the proposed method performs competitively compared to traditional alignment methods. The proposed training method enables LLMs to perform robustly in multi-turn reasoning tasks with both in-domain and out-of-domain conditions.

Cognitive Field Theory (CFT) proposes that cognition arises from memory-dressed collective dynamics that generate a persistent macroscopic cognitive field. Here we develop a Cognitive Field Network (CFN), a recurrent Transformer in which the organized hidden field re-enters subsequent inference through \[ Φ_{n+1}=F_θ(X_{n+1},Φ_n). \] Rather than prescribing an explicit memory operation, the CFN allows new information to act on an already history-dependent collective state. We find that learning organizes persistent, content-dependent recurrent dynamics whose timescale increases systematically with the trained recurrent horizon. Semantic continuation propagates the recurrent state far beyond this horizon without replay of the target answer. Without content-specific support, the field exhibits finite passive relaxation, whereas periodic re-exposure to relevant input repeatedly renews the surviving state and drives it toward an approximately stationary nonzero regime. Unrelated-input and recurrence-off controls do not reproduce this behavior, while near-paraphrased re-exposure produces weaker renewal, demonstrating representation-sensitive persistence. These results distinguish three dynamical processes: collective memory dressing forms and sustains a history-dependent cognitive field, structured input reorganizes this field, and cross-cycle re-entry makes the resulting state causally available to subsequent inference. The CFN therefore provides a controlled computational platform for studying persistent, history-dependent cognitive dynamics without a separately prescribed memory system.

We give deterministic and uncoupled learning dynamics for finite multiplayer general-sum games under full-information feedback that achieve constant individual swap regret, independent of the horizon $T$. With $n$ players and at most $m$ actions each, the individual swap regret of every player is $O(\sqrt{n} m \log m \log^{5/2}(nm))$ at every finite horizon. Each player predicts the deviation gains, then uses these predictions to update a row-stochastic transition matrix, and plays its stationary distribution. The proof combines a potential argument exploiting stationarity with a two-scale higher-order prediction analysis, using rooted-tree representations to handle the nonlinear dependence of deviation gains on the stationary distributions. An adversarially robust variant, obtained through a generic common-prefix switching wrapper, preserves the self-play bound up to a universal constant and guarantees individual swap regret at most $7\sqrt{m T \log m}$ in the adversarial setting.

Action Chunking Transformers (ACT) are widely used to learn robot manipulation from demonstrations. Their conditional variational autoencoder includes an encoder meant to capture differences between demonstrations during training. The original ACT paper reported that encoder removal dropped the mean success rate from 35% to 2% on two simulated tasks with human demonstrations. We re-ran this ablation in the original code and checked whether the findings depend on the implementation or training data. The published drop does not reappear in our tests, although smaller gains or losses in success rate remain uncertain. To investigate the discrepancy, we varied training length and how checkpoints are selected for evaluation. Both can reverse which policy scores higher, but the published drop's cause remains unknown. Success rates alone leave open whether the encoder provides information that helps the policy reconstruct demonstrated actions. On the tested ACT benchmark, the sampled latent provides little reconstruction benefit at every tested nonzero weight of the penalty on latent information. At inference, ACT leaves this latent unused and sets it to zero. Skipping the encoder increases training throughput in both implementations we timed. We release code, evaluation tools and results so others can repeat the comparisons and test the encoder on other tasks.

Background: Large language models (LLMs) have achieved physician-comparable performance on multiple-choice medical knowledge examinations, but their capabilities in clinical history taking, urgency assessment, and safety remain insufficiently evaluated. We proposed Japanese Stroke LLM Evaluation, a multi-turn conversational benchmark for stroke care in Japanese, and evaluated LLM performance and safety under practice-oriented conditions. Methods: We created 10 stroke and related-condition cases and evaluated LLMs in multi-turn Japanese conversations. The LLM acted as physician, while a board-certified neurosurgeon acted as simulated patient and evaluator. Each case comprised history-taking and action phases scored using pre-specified criteria. Errors that could directly threaten life were defined as critical mistakes. The safety threshold was at least 80% overall with zero critical mistakes. Eighteen models were evaluated in October 2025 and June 2026. Results: Claude Fable 5 achieved the highest score (87.4%) with zero critical mistakes, followed by Claude Opus 4.7 (80.3%) and GLM-5.2 (75.6%). Two leaders met the safety threshold. Eleven models made 17 critical mistakes, including failure to confirm laboratory results or blood glucose before t-PA, surgery before airway stabilization, omission of cervical vascular evaluation, and t-PA outside its indication. History-taking question count correlated with history-taking score (r = 0.648, p = 0.007). Conclusions: Japanese Stroke LLM Evaluation provides a benchmark for LLM performance under practice-oriented conditions, including a cap on history-taking questions. Cases and evaluations were created by neurosurgical specialists rather than using an LLM-as-judge approach. Performance improved across cloud-based and on-premise models in 2026, with some exceeding the safety threshold. Further evaluation using real-world cases is required.

Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first memory middleware with typed stores, retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated prompt tokens. A fourth, dense dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.

Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: prior-free variants regress canonical (NOCS) coordinates directly from local observations and implicitly memorize the canonical frame in the weights, which ties the parameters to category-typical orientations and hurts generalization under distribution shift; prior-based variants introduce a category prior but typically follow a serial deform-then-align pipeline, where underconstrained canonical completion can corrupt correspondences and induce error cascades in pose. We propose PriorPose, a reference-guided correspondence framework that keeps the category prior explicit and solves canonicalization and alignment jointly in a shared feature space. A reference-guided seeded transformer embeds the partial observation and the category prior as token sets and fuses them via geometry-aware seeds, from which the network jointly predicts a per-point NOCS field for visible points and a canonical deformation of the prior that reconstructs a full canonical instance, while a deep pose head regresses $(R,t,s)$ from the induced correspondences. A two-part shape consistency objective, with canonical-space and camera-space consistency losses, couples correspondence, deformation, and pose, reducing reliance on memorized canonical orientations and avoiding deform-then-align error cascades. Experiments on standard and larger-category benchmarks demonstrate that PriorPose sets new state-of-the-art results on most evaluated metrics, especially under strict pose thresholds, while remaining competitive on relaxed pose and IoU metrics and showing improved robustness under shape variation and domain shift.

Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose different risks to different ego trajectories. We present CorrRisk-WM, a planning-oriented partial world model coupling environment evolution with supervised intrusion and near-miss prediction over bounded candidate-trajectory corridors. A latent environment model recursively predicts agent states and updates agent-agent and agent-map interactions. Each candidate queries the evolving environment through footprint- aware geometry and learned agent-corridor representations. A lightweight recurrent risk module uses temporal context to estimate per-slice hazards; survival aggregation yields first-entry and horizon-level event probabilities. On 29,176 scenarios from 100 Waymo validation shards, CorrRisk-WM achieves intrusion average precision (AP) of 0.8567 and 1-m near-miss first-entry AP of 0.8671. In baseline comparisons, it attains the highest near-miss AP at all three distance thresholds and the lowest observed open-loop collision rate (4.88%), with route progress of 15.35 m. Across three seeds, removing dynamic environment modeling or candidate-conditioned geometric interaction reduces mean intrusion AP from 0.8590 to 0.7624 and 0.7252, respectively. These results support coupling environment evolution with candidate-conditioned geometric reasoning for risk prediction and safety-oriented candidate selection.

Strong $χ^{(2)}$ interactions at low optical powers are key to scalable nonlinear and quantum photonics. Although doubly resonant microresonators exhibit exceptional efficiencies, they require simultaneous resonance and phase matching of widely separated optical frequencies, making them inherently sensitive to fabrication and operating conditions. Singly resonant cavities eliminate this constraint by resonating at only the fundamental frequency while the second-harmonic field propagates in a single pass, but they have traditionally sacrificed nonlinear efficiency. Here, we demonstrate a singly resonant InGaP-on-insulator microresonator that overcomes this tradeoff. Combining the large $χ^{(2)}$ nonlinearity of InGaP with high-quality-factor resonators, we achieve efficient and widely tunable second-harmonic generation, broadband quantum-frequency-comb generation, and low-threshold optical parametric oscillation. Unlike conventional centimeter-long singly resonant devices, our millimeter-scale InGaP devices deliver nonlinear performance comparable to, and even exceeding, doubly resonant systems. By overcoming the conventional efficiency-robustness tradeoff of singly resonant devices, this work opens a new route to low-power, broadband, and widely tunable $χ^{(2)}$ nonlinear and quantum photonics.

Continuous-time (CT) machine learning has emerged as a principled framework for modeling temporal dynamics as a continuous process, particularly when observations are sampled at arbitrary time points or span long-range horizons. However, major branches of CT machine learning have matured in separate research communities, leaving their mathematical relationships and design trade-offs insufficiently characterized. In this survey, we develop a unified, concept-driven view of major CT machine learning branches through a taxonomy that organizes families according to their underlying base mathematical formulations. We present a canonical mathematical formulation that relates these families through different architectural choices of vector-field parameterization, stochasticity, memory mechanisms, and discretization. We compare training algorithms, optimization strategies, and failure modes, highlighting the trade-offs across families. We further provide a comparative analysis of theoretical computational complexity alongside an illustrative architecture-controlled benchmark analysis on representative architectures from each family. We also review software ecosystems supporting their implementation. Finally, we identify open challenges in approximation theory, training stability, hardware-efficient implementations, benchmarking, foundation models, and scientific machine learning, and discuss an agenda for future research.

Physical AI requires more than increasingly large robot datasets: intelligent robots acquire knowledge through continuous interaction with the physical world. We argue that the defining scientific resource of Physical AI is therefore not raw robot data alone, but robot experience - physically grounded interaction whose observations, actions, embodiment, context, and outcomes preserve the perception-action-consequence loop. We introduce the Robot Data Factory (RDF), a mission-driven infrastructure and methodology for continuously generating, validating, benchmarking, and reusing such experience. RDF organizes heterogeneous robots and environment-specific training grounds through reproducible missions, skill curricula, synchronized multimodal sensing, external ground truth, an agentic robot network, data pipelines, and living benchmarks. Rather than treating datasets as static end products, RDF implements a closed Deploy-Measure-Learn-Repeat cycle in which validated physical experience supports world models, vision-language-action models, embodied policies, digital twins, and subsequent robot deployment. We further formalize robot experience and its quality, introduce a mission-task-skill-episode-dataset-benchmark-capability hierarchy, and derive quantitative scaling laws and an algorithmic synthesis procedure connecting robot fleet size, sensor rates, storage, learning representations, tokenization, training compute, inference, and latency to Embodied-AI cluster requirements. The framework is instantiated in three complementary physical training grounds for domestic, environmental, and energy applications. RDF thus reframes robot data generation as a continuous scientific production process and provides a pathway toward reproducible, scalable, and eventually federated infrastructure for Physical AI.

World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when execution departs from expectations. Although progress is often measured by visual fidelity, their value lies in improving behavior. Before reaching for a cup, a person anticipates its weight and resistance to grasping, shaping the hand before contact. Such anticipation is coarse and rarely pictorial, yet it guides action. This raises a central question: which predictive capabilities improve behavior? Existing surveys, organized by architecture, output modality, or application domain, leave this question implicit. We introduce three progressively stronger capability levels: Plausible models preserve task-relevant temporal, geometric, or physical structure; Controllable models additionally predict how interventions alter that structure; and Actionable models translate predictions into measurable gains in planning, action, learning, evaluation, verification, recovery, or data selection. We complement this hierarchy with a 3 x 4 matrix crossing geometry, physics, and action grounding with improvement loops centered on data, rewards, policies, and the model itself. Using this framework, we survey manipulation, navigation, locomotion, autonomous driving, and general embodied learning, tracing technical progressions, clarifying capability requirements, and examining datasets, benchmarks, and evaluation protocols. We identify challenges in long-horizon consistency, uncertainty calibration, causal intervention testing, latency, verification and recovery, and cross-embodiment transfer. This perspective shifts evaluation from visual plausibility toward whether predictions capture task-relevant state, reflect intervention effects, and improve the closed-loop behavior of embodied agents.

Large-scale pre-training has transformed representation learning in 2D vision, yet its transferability to 3D single object tracking (SOT) remains insufficiently understood. Directly fine-tuning self-supervised 3D encoders, such as masked autoencoders (MAE), often leads to sub-optimal adaptation because the reconstruction objective is not fully aligned with the spatial-temporal matching requirements of tracking. In this paper, we observe that this difficulty can be interpreted as a layer-wise transfer mismatch: shallow layers tend to preserve transferable geometric cues, while deeper layers become increasingly specialized to the reconstruction pretext task and are less suitable for downstream tracking. Based on this observation, we propose MAETrack, a lightweight adaptation framework for transferring pre-training MAE representations to 3D SOT. MAETrack includes Layer-Selective Initialization (LSI), which initializes only the shallow stages of the tracking backbone from pre-trained weights while re-initializing deeper stages, and Geometric Residual Gating (GRG), which reinforces structurally salient regions in the search BEV features before template-search fusion through residual spatial modulation. Extensive experiments on standard 3D SOT benchmarks show that MAETrack consistently improves upon vanilla fine-tuning baselines with limited computational overhead. More broadly, our results suggest that effective transfer from 3D reconstruction pre-training to 3D tracking is not merely a matter of partial fine-tuning, but depends on a tracking-oriented transfer principle that preserves shallow geometry while adapting deeper representations to the downstream objective.

While optical manipulation of atomic arrays has reached a high degree of precision and scalability, the stable optical confinement of solution-based artificial atoms like colloidal quantum dots (CQDs) remains hindered by weak trapping forces and thermal fluctuations. High-intensity trapping often compromises the quantum properties of these emitters, creating a significant trade-off between mechanical stability and optical integrity. To overcome this, we propose encapsulating CQDs within a transparent polymer matrix, thereby increasing the effective interaction volume and optical restoring force without altering the emitters themselves. This strategy allows for stable spatial confinement under standard experimental conditions, as evidenced by the direct resolution of positional fluctuations through photoluminescence imaging and trajectory tracking. With averaged position fluctuations below 20 nm, the intrinsic emission spectra and photoluminescence decay dynamics remain largely unaffected, and photon-correlation measurements confirm the full preservation of single-photon emission. These findings establish a robust method for the controlled confinement of colloidal quantum emitters and in-situ quantum-optical measurements for future advancements in quantum-optical manipulation of artificial atoms.

Learning manipulation from human video requires high-fidelity hand-motion reconstruction in metric units. Today's metric hand labels come from studio rigs and instrumented headsets, and both are confined in the same two ways: neither leaves a prepared setting, and neither is checked against an independent reference. Unconstrained head-worn recording promises the opposite trade-off, scaling with the number of people wearing a device. We therefore introduce MEgoVista, an offline pipeline that turns a single unprepared MEgo View recording into metric two-hand and head motion in one gravity-aligned world frame. Three properties set it apart from existing egocentric reconstruction systems: first, it reconstructs in settings studio volumes and tabletop rigs cannot reach, settling hand ownership at detection so bystander hands stay out of the wearer's trajectory; second, it takes its metric gauge from calibrated stereo rather than a monocular prior, installing scale at initialisation so policies receive physical units, not arbitrary coordinates; third, both outputs are scored inside a motion-capture volume against independent Chingmu optical capture, under a protocol that audits its own reference and charges what a method declines to predict. MEgoVista is offered as a measured route from egocentric video to metric hand supervision, one that widens where such labels can be gathered.

Learning humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both robot and object motion. Human demonstrations provide examples of coordinated interaction, but transferring these behaviors to humanoid robots requires learning how to establish and maintain effective contacts under different embodiments and dynamics. We present Weave, a unified framework for learning whole-body dexterous humanoid-object interaction from captured human demonstrations. Weave first converts captured human-object interactions into executable robot-object references through contact-aware retargeting and approach-motion completion. At its core is a contact- and geometry-aware policy that jointly commands 29 body joints and 12 actuated finger joints across multiple objects and interaction sequences. Evaluation across nine objects yields a 92.5% success rate on trained interactions and, without any additional training, 65.0% on sequences never seen during training. We additionally release ~9,000 physically executed rollouts spanning ~23 hours, providing robot-object trajectories with contact annotations for downstream interaction-policy learning and physically consistent HOI motion generation. Project website: https://xiaohu-art.github.io/Weave/

Manufacturing consumes one third of global energy and still has significant room for improvement in terms of energy efficiency. Optimal process control is essential for this purpose. However, synthesizing mathematical optimization models from messy, real-world industrial specifications requires bridging unstructured natural language and spatial diagrams with rigorous mathematical syntax. This poses a profound challenge for general-purpose Large Language Models (LLMs), which may introduce invalid constraints when tasked with modeling continuous multi-physics dynamics. To address this, we introduce little m, an AI agent designed to assist the formulation of industrial process control models. Combining a domain-specific knowledge repository with LLM-driven interaction, the proposed framework formulates real-world optimization problems as mathematical models. For systematic evaluation, we introduce the Industrial Process Control Benchmark (IPC-Bench), a novel multimodal dataset of 50 canonical scenarios requiring joint reasoning over text and process diagrams. Through comprehensive automated structural assessments and double-blind human evaluation, little m substantially outperforms state-of-the-art LLMs, generating semantically correct models. These evaluations assess formulation quality rather than solver feasibility, formal physical validity, or closed-loop industrial performance. The implementation of little m and the IPC-Bench dataset are available at https://github.com/yeyongchao/process-modeling-benchmark.

Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems model players and game dynamics, support design and development, adapt player-facing experiences at runtime, and evaluate resulting artifacts. Yet these directions have evolved largely separately, obscuring which capabilities transfer across settings and which remain tied to particular games, engines, interfaces, or player populations. We organize the literature into six roles according to the immediate use of AI output: playing and acting; modeling players and games; designing games; building and maintaining games; generating and adapting at runtime; and testing and evaluating games. For each role, we examine what structure is supplied by the game or workflow, what AI learns or produces, which capabilities and artifacts transfer across settings and roles, and what evidence supports the claims. We identify cross-role connections: trajectories train world models, learned environments provide experience for agents, design specifications drive executable implementations, and play or testing feedback guides revision. However, control schemes, rules, engine interfaces, state representations, and player contexts often remain setting-specific, so downstream claims require validation in the target setting. Evaluation is most standardized for bounded game playing and selected learned environments, while persistent state in learned worlds, repeated software revision, validated player modeling, sustained runtime adaptation, and representative automated testing remain less established. The central challenge is to reuse or transfer outputs and capabilities across roles while re-establishing evidence for effectiveness in the game-specific contexts where they are used.

Background and Objective: Colonoscopy recording practice preserves text reports and still photographs, while the spatial information already present in the recorded video - where the scope traveled, where a lesion was observed, and whether the same lesion was seen again - is discarded when the procedure ends. This study determines whether a lesion-centered spatial record can be assembled and validated without full-colon 3D reconstruction. Methods: A four-layer hierarchical pipeline was assembled - (1) a global topological map, (2) lesion-level spatio-temporal tracks, (3) on-demand local 3D reconstruction, and (4) persistent lesion identity across repeated observations - and ran end to end on four public videos (two C3VDv2 sequences with ground-truth depth and two full REAL-Colon procedures; 40,245 frames). All components are published, individually validated methods; the contribution is their lesion-centered assembly, linking rules, and evaluation. Results: Revisits, impossible under forward-only mapping by construction, were detected by entry-map Bayesian localization: 5,614 and 4,043 revisit events (56 and 68 distinct nodes) in the two full procedures. Lesion-identity merging at the adopted threshold 0.5 maintained ground-truth purity 1.0 while auto-merging 20 of 231 candidate pairs. The endoscopy-specific geometry engine outperformed a general-purpose foundation model on all metrics (overall absolute relative error (AbsRel) 0.2276 vs. 0.3523). Conclusions: The results are partial but establish a concrete near-term path: revisit detection, lesion identity, and local 3D each returned quantitative, reproducible output without waiting for complete geometric reconstruction; validating the record on clinical data is the next step.

Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritizes semantic invariance, which often suppresses subtle perceptual signals, a phenomenon we term perceptual submergence. Furthermore, standard preprocessing techniques (e.g., cropping and interpolation) further exacerbate the loss of critical high-frequency quality cues. In this paper, we propose the Cross-modal Perception Alignment Adapter (CMPA), a manifold-aware framework designed to disentangle perceptual distortions from dominant semantics. CMPA introduces a Perception-Sensitive Feature Extractor (PFE) that projects CLIP features into a compact, low-dimensional subspace, explicitly magnifying distortion-induced off-manifold deviations. Subsequently, a Cross-Modal Perception Alignment Injector (PAI) aligns these features with quality-aware text anchors and re-injects them into the backbone. To ensure input fidelity, we also devise a Residual-enhanced Perceptual Downscaling strategy that adaptively compensates for resolution-induced information loss using Just Noticeable Difference (JND) guided frequency re-injection. Extensive evaluations on several benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, effectively recovering the perceptual signals submerged in semantic-dense representations.

State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision through ViM, VMamba, and Visual State Space Duality (VSSD). Yet the low-bit post-training quantization (PTQ) behavior of VSSD remains insufficiently understood. A weight-activation split on VSSD-Tiny identifies activation quantization as the dominant low-bit bottleneck, while representative inputs to selected VSSD-backbone linear layers exhibit strong channel-wise magnitude variation and token-localized extremes. We propose the Channel-wise Token-balanced Output-Aware Clipping (CTOAC) method, which learns per-input-channel clipping bounds by minimizing a token-balanced reconstruction loss on the corresponding linear outputs. Only the selected linear layers and their input activations are quantized; other backbone operations retain their original precision. Across VSSD-Tiny, VSSD-Small, and VSSD-Base, the proposed CTOAC method retains ImageNet-1K accuracy and remains substantially more robust than the evaluated baselines at more aggressive precision settings. Applying the same quantization scope to VSSD backbones on COCO and ADE20K preserves strong object detection, instance segmentation, and semantic segmentation performance. An optimized RTX 4090 deployment configuration achieves up to 1.42x end-to-end speedup over FP32.

Reinforcement learning (RL) post-training drives the frontier capabilities of large language models, with its wall-clock dominated by autoregressive rollout generation. Speculative decoding is an established remedy for this bottleneck, but existing draft heads must be pretrained or warmed up before RL, introducing substantial training cost outside the RL run to be accelerated. We observe that RL training itself provides both conditions required for online draft-head training: its rollout distribution is far narrower than that of pretraining, and its verification step continuously produces supervision signals aligned with this distribution. Building on these observations, we propose GrowMTP, which uses this supervision to train a draft head from scratch entirely within the RL loop, with all head updates detached from the policy backbone. On Qwen3-4B (no draft head), MiMo-7B-SFT (weak head), and Qwen3.5-4B-Base (strong head), GrowMTP achieves rollout speedups of 2.13x, 1.93x, and 1.36x, and end-to-end speedups of 1.60x, 1.41x, and 1.20x, respectively. GrowMTP therefore serves existing RL training frameworks as a modular component, particularly offering a from-scratch acceleration path for models without pretrained draft heads.

Gender bias in large vision-language models (LVLMs) undermines their fairness and reliability, compromising output trustworthiness. Current mitigation methods rely on training-phase adjustments or post-hoc calibration, but face limitations in dynamic visual bias mitigation. These include inability to capture real-time visual-textual incongruence, dependence on predefined gender bias taxonomies, and degraded cross-modal alignment with emergent bias patterns. To address these challenges, we propose ViD, a causally-inspired framework that analyzes attention mechanisms across five distinct patterns, revealing confounding effects from strong language priors. ViD demonstrates that visual-to-language cross-attention effectively suppresses bias while preserving general reasoning capabilities and text generation quality. ViD incorporates dual mechanisms: backdoor adjustment counters strong language priors, while refined token selection in decoding layers optimizes processing. This enhances model robustness and inference efficiency. Our integrated approach significantly mitigates gender bias across multidimensional social attributes in LVLMs, improving visual grounding and output fairness. Cross-benchmark validation shows ViD reduces gender bias by 14.7\% on single-attribute evaluations (FACET) and achieves significant improvements on image captioning tasks (MS COCO), with gender bias score improving from 0.6708 to 0.9978 for LLaVA. Crucially, these improvements require no additional training overhead, making ViD a scalable and practical solution for bias mitigation in LVLMs.

When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instruments for understanding behavior. We address this by asking: can we use large vision-language models (LVLMs) as experimental instruments for studying their own failure dynamics? Focusing on visual hallucination, we introduce SAFE, a training-free decoding framework that contrasts visually-grounded and vision-ablated generation paths to produce a token-level contrastive grounding score that identifies when the model favors linguistic priors over visual evidence. This signal serves dual roles: as a practical proxy for detecting visually-ungrounded tokens, and as the basis for decoding-time penalties. Our analysis yields three empirical observations: visual dependency decays over generation, hallucinations co-occur in temporal clusters, and early intervention reduces clustering without substantially degrading fluency. On MMHalBench, SAFE substantially outperforms all compared baselines; results elsewhere are more mixed. We argue that designing contrastive probes exemplifies a broader mission: using models as instruments for scientific understanding. Code: https://github.com/zhaozhipeng1997/SAFE_public.

World Action Models (WAMs) offer a promising approach to general-purpose robot manipulation by jointly modeling visual dynamics and actions. However, most WAM studies focus on tabletop or arm-centric manipulation, while humanoid loco-manipulation remains less explored. To address this gap, we introduce WholeBodyWAM, which jointly predicts future visual dynamics, manipulation actions, and whole-body control intents for generalizable humanoid loco-manipulation. It preserves pre-trained world-action priors while grounding heterogeneous whole-body controller (WBC) semantics and coordinating whole-body behavior. Extensive experiments show that WholeBodyWAM achieves an overall simulation task success rate of 91.9%, with a 0.23 improvement in real-world out-of-distribution task progress and a 70% reduction in success-rate variance across WBCs relative to the respective baselines. These results suggest a path toward scalable humanoid whole-body intelligence by extending pre-trained world-action priors through structured WBC grounding and coordination, rather than relearning whole-body behavior from scratch. Project page: https://wholebodywam.github.io/.

Vision-language-action (VLA) models have become the dominant paradigm for language-conditioned robot manipulation. However, although images and language instructions inherently encode geometric information, VLAs acquire their spatial competence purely from demonstrations. As a result, they are reliable only within the range of scene poses that the demonstrations cover. We propose SAVLA, an end-to-end symmetry-aware VLA model for robust and data-efficient policy learning. Our approach keeps the pretrained vision-language backbone entirely frozen while combining it with an equivariant flow-matching action head and a learned canonicalizer. The head decomposes its state, action, and conditioning inputs into invariant and equivariant channels, and preserves this typing throughout all of its layers. The canonicalizer transforms oblique-view images into a canonical frame and rotates the geometric conditions consistently. We evaluate our model on LIBERO. Compared with the GR00T N1.5 baseline, SAVLA improves the success rate averaged over all four LIBERO suites by 5.1 points and increases the mean success rate under rotation on LIBERO-Goal from 41.5% to 90.4%.

Continual post-training of large multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in opposite directions. SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting; on-policy methods such as RLVR and self-distillation preserve policy proximity yet supply little signal when the policy cannot yet solve the task. We introduce ReDraft (Reference-Driven Revision and Fine-Tuning), which obtains both from the model's own failures: using an expert response only as a reference, it has the model revise its own incorrect rollout, keeps the revision only if a verifier accepts it, and fine-tunes on what survives. Each retained target is therefore explicit, yet still close to the current policy. Across Counting, Clock Reading, and Jigsaw on Qwen2.5-VL-3B/7B, two of them with near zero accuracy, ReDraft gains 56.9 points on the target task against SFT's 52.9 while cutting prior-task loss from 16.6 to 1.5 points (11.3x less forgetting), and improves on OPSD along both axes (19.3 gain, 6.2 loss). Data- and parameter-space analyses match the design: revised targets are more probable under the base model, and the updates they induce stay compact and follow SFT's direction more closely than OPSD's. Repairing the model's own output, rather than replacing it with an expert's, is what lets one objective do both.

Computer-use agents increasingly operate browsers, software, and desktop applications via CLI or API portals, but graphical user interface (GUI) still plays an important role in common industrial production scenarios. GUI agents commonly employ fresh observe-plan-ground-act loops, which is inefficient for enterprise tasks that repeatedly update records, process forms, configure tools, and export reports. We introduce EchoPath, a model-agnostic harness that converts artifact-validated GUI trajectories into standardized, parameter-controlled callable memories, analogous to Model Context Protocol (MCP)-style tool calls rather than unstructured experience records. Each memory stores task-intent keys, application and state preconditions, flexible input parameters, GUI evidence, validation provenance, and lifecycle state, so the host agent invokes a targeted procedure only when it can be deterministically replayed in the current runtime. The core mechanism enabling replay is an image-based target-reaiming algorithm that treats stored coordinates as visual evidence, matches the remembered GUI target against the current screen, and emits corrected operation coordinates before execution. During replay, EchoPath rebinds only declared modifiable inputs and rejects ambiguous or incompatible steps to bounded grounding repair or fresh planning. In experiments with real computer-use tasks, EchoPath reduced median token cost by more than 90% and median execution time by about 60%. These results support a bounded form of enterprise GUI memory: validated execution experience can become a controllable callable asset for recurrent work rather than only context for another reasoning pass.

Virtual try-on (VTON) enables customers to visualize how fashion products appear when worn and has become an important technology for online shopping. While recent advances have substantially improved garment VTON, jewelry remains a challenging and underexplored category due to its small size, rigid structure, and sensitivity to fine-grained visual details. Realistic jewelry VTON requires not only faithful appearance transfer but also accurate scale and placement relative to the wearer. Existing jewelry VTON methods typically rely on mask guidance, whereas mask-free approaches lack explicit guidance for modeling the product scale. To bridge this gap, we introduce JVTO-Bench, a benchmark dataset for scale-faithful jewelry VTON, providing reference source target triplets with real-world product-scale annotations across four major jewelry categories. Building upon this benchmark, we propose JewelTry, a mask-free diffusion framework for scale-aware jewelry VTON. JewelTry incorporates a scale adapter that encodes product dimensions into a scale token, enabling the model to learn scale relationships between jewelry items and surrounding human anatomy in-context. To further improve jewelry consistency, we introduce a single-directional condition attention mechanism and an attention refinement loss that preserve both coarse geometry and fine-grained structural details of the reference jewelry. Extensive experiments show that JewelTry achieves a balance among visual fidelity, background preservation, object consistency and scale accuracy, establishing a strong baseline for mask-free, scale-aware jewelry virtual try-on.

How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination of feedback from stakeholder teams, domain expertise, and insights from data analyses. Yet the nuances of how and where recommendations perform well or poorly for end users are difficult to discern from aggregate quantitative metrics. Whereas these metrics provide a high-level and incomplete picture, further granularity into the quality of recommendations and their patterns requires reasoning with domain understanding and objectivity, at scale. We contemplate this complex conundrum and describe a method and implementation that uses the latest AI agentic advances to provide actionable diagnoses and improvements for production recommender systems. We present AURA (Agentic Understanding and Refinement of recommender Algorithms), an end-to-end agentic system that performs qualitative evaluation at scale and can then generate improvements to our algorithms at the code level. Specialized agents read production engagement logs, from thousands of sessions to millions, and surface patterns and examples of how the recommender fails real users. The next step uses those diagnoses and context about the recommender's own code, data, and training pipeline to propose and implement refinements grounded in that codebase. We report the system design, initial tests on production data from two large consumer platforms at a major media-streaming company, safeguards, operational learnings, and early results toward a self-improving recommender system. Finally, the diagnostic gap AURA closes is not specific to streaming. The architecture is built to transfer: every domain-specific element enters through the configuration layer that already ported it between our two platforms. We map it concretely to e-commerce and online-retail recommendation.

Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution shift and accumulate under recursive deployment. We develop a variational approach to this problem by introducing latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions. The framework is formulated directly on function spaces and specialized to functional Gaussian models, where structured latent perturbations induce a spectral geometry and variational transition alignment regularizes the learned dynamics. We further analyze how these mechanisms affect autoregressive error propagation, providing a theoretical connection between variational training and long-horizon prediction. We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition. Empirically, we demonstrate the effectiveness of VAMO on several fluid-dynamics benchmarks with prediction horizons extending substantially beyond those represented during training, where it consistently reduces error accumulation and improves rollout stability over several deterministic and noise-injection baselines. Overall, these results highlight variational modeling as a complementary approach to robust long-horizon neural PDE dynamics.

Thin-film barium titanate (BaTiO3, or BTO) has emerged as a promising electro-optic (EO) material for integrated photonics due to its exceptionally large Pockels coefficients, low optical loss, and compatibility with heterogeneous integration. Recent advances in epitaxial thin-film growth, crystal orientation control, ferroelectric domain engineering, and scalable integration have enabled EO performance in thin-film BTO approaching bulk-like properties on photonic platforms. This review provides a comprehensive overview of integrated photonic devices based on thin-film BTO, including fundamental material properties, thin-film growth and integration strategies, passive waveguide configurations, EO response at both the film and device levels, and relevant optical applications. We review the role of film orientation, domain structure, and device geometry in determining accessible EO coefficients and modulation mechanisms, as well as the distinctions between intrinsic and effective EO responses demonstrated at the film and device levels. Representative studies are compared in terms of film-quality-related metrics and device performance figures of merit, alongside emerging applications realized in BTO-based platforms. Finally, we discuss the remaining challenges and outline future development directions toward high-performance BTO-based integrated photonic systems.

Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves open whether spoken dialogue models can sustain diverse roles over extended interactions, especially beyond predefined fictional characters. We introduce RoleBreak, an open benchmark for long-horizon role-playing robustness in spoken dialogue. RoleBreak contains 310 character-based and user-centered roles, 6,688 human-verified dialogue turns, and 11,743 fine-grained evaluation criteria, with 1,856 turns carrying expressive emotion targets for evaluating vocal emotion. Its scenarios are designed to stress role consistency, interaction quality, safety, and affect over extended conversations. We evaluate nine configurations spanning full-duplex, omni-modal, and cascaded ASR--LLM--TTS paradigms. We find four key patterns. First, current systems are substantially stronger at semantic role adherence than at vocal emotion. Second, semantic robustness remains brittle over long interactions: even the strongest evaluated system encounters its first persona and safety failures after only 10.4 and 11.6 turns on average. Third, scaling the LLM substantially improves semantic robustness and delays failure, but yields little improvement in vocal emotion. Finally, user vocal emotion affects role-playing behavior even when linguistic content is fixed. These findings highlight persistent gaps in both long-horizon robustness and vocal expressiveness in spoken role-playing systems.

Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, placing joint demands on the integrated spatial intelligence of today's foundation VLMs. Existing spatial-intelligence benchmarks primarily evaluate isolated judgments of relations, directions, or targets and therefore do not directly measure the integrated navigation ability required to combine target recognition, action-consequence assessment, distance estimation, and path planning. To fill this evaluation gap, we introduce EgoPathBench, a dataset and five-task benchmark for first-person waypoint decision-making. Each question presents an egocentric RGB image, a natural-language goal, and numbered visible waypoints; a model returns traversable candidates or an ordered route. Predictions are evaluated for candidate feasibility, adjacent-edge legality, and goal arrival under point-agent or embodied geometry. EgoPathBench contains 31,852 training, 1,345 validation, and 1,111 benchmark questions and retains at least one geometrically verified reference route for every route question. Across nine VLMs, the highest EgoPath Score is only 28.3. The top-ranked model reaches 35.9% success on Point Path, but only 2.9% and 4.0% on Embodied Path and Intent Path, respectively, showing that current models remain limited in forming complete, goal-consistent routes under embodiment constraints. Beyond the evaluation data, we release the corresponding training resource. Fine-tuning Qwen 3.5 4B on the released training split raises its EgoPath Score from 3.9 to 38.9 and improves all four reported evaluations across three external spatial benchmarks, with gains of 1.4--9.6 points.

Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large language models (LLMs) for high-level decision-making. However, the slow, stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.

Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and existing policies rarely model how these cues evolve under actions, making them brittle under contact uncertainty. To address these, we present ProxiDex, a dynamics-guided proximity policy framework that treats hand-object proximity as an interaction state for dexterous manipulation. ProxiDex reconstructs interaction point clouds and converts geometric distances into proximity cues, forming a hardware-agnostic contact representation that provides immersive feedback during VR teleoperation. Built on this representation, ProxiDex learns action-conditioned proximity dynamics with a coupled forward-inverse design: future observation latents are predicted from actions, while proximity variations are decoded from latent changes. Leveraging these dynamics, ProxiDex adaptively reweights proximity tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference, stabilizing action generation under unreliable visual feedback. Simulation and real-world experiments demonstrate improved success rates and robustness over representative baselines across standard, unseen objects, and perturbation scenarios. Additional visualizations are available at https://proxidex.github.io/.

Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has shown promise, existing methods can be improved to better guide attention toward causal evidence and strengthen feature discrimination. To address this, we propose a novel training framework that enhances counterfactual contrastive learning for VQA. Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers, Answer-Contrastive (AC) loss to refine the prediction space and Gradient-Discrepancy (GD) loss to enforce causal visual grounding. Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, yielding a small generalization gap of 1.16%. This demonstrates a strong balance between OOD robustness and in-distribution performance.

Puns are a challenging form of figurative language that exploit phonetic similarity and semantic ambiguity to convey multiple meanings. Although large language models (LLMs) demonstrate strong language understanding capabilities, they still struggle with pun reasoning due to limited phonetic modeling and uncontrolled end-to-end generation. We propose \textbf{PunGraph}, a retrieval-enhanced knowledge graph framework for pun understanding. PunGraph constructs a phonetic-semantic lexical graph using the Unisyn phonetic dictionary, IPA and G2P representations, and WordNet definitions, and retrieves candidate words or senses to constrain LLM reasoning within a structured candidate space. We further introduce \textbf{WebPun}, a new large-scale dataset containing 5,730 annotated heterographic and homographic puns. Experiments on SemEval-2017 and WebPun show that PunGraph consistently improves the performance of small-scale LLMs and achieves competitive results against strong proprietary models. Further analysis shows that retrieval-guided phonetic and semantic constraints effectively reduce common reasoning errors in pun interpretation, highlighting the benefits of integrating structured knowledge with LLMs. We release our code and dataset at https://github.com/ysu132/PunGraph.

Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedding predictive architectures (JEPA) differ in the space in which their targets are defined, yet existing ultrasound studies compare them under different corpora, backbones, and evaluation protocols. We compare these three objective families using the same encoder backbone, pretraining corpus, optimisation schedule, and frozen-evaluation protocol. Encoders are pretrained on COVID-BLUeS LUS videos and evaluated with linear, $k$NN, and attentive probes at 5\%, 10\%, 50\%, and 100\% label budgets. Evaluation is performed on POCUS using patient-level five-fold cross-validation and on the independently acquired Mendeley-Uganda dataset, which is excluded from both pretraining and probe fitting. At the full label budget under linear probing, VideoMAE and V-JEPA achieve $66.5 \pm 13.1$ and $65.4 \pm 11.7$ balanced accuracy on POCUS, while MoCo achieves $42.1 \pm 1.2$. On Mendeley-Uganda, the ranking reverses: MoCo performs best at $62.7 \pm 1.0$, followed by VideoMAE at $53.8 \pm 2.8$, while V-JEPA falls near chance at $35.1 \pm 4.9$. These results show that POCUS probe accuracy alone does not identify the objective that transfers best across datasets. We also outline planned representation-level analyses to examine this reversal. Code is publicly available at https://github.com/moeinheidari7829/LUSVideoSSL.

State Space Models (SSMs) have emerged as a compelling alternative to Transformers, enabling sequence modeling with constant memory and linear compute. Although SSMs exhibit reasonable performance and favorable computational characteristics, they continue to lag behind Transformers on tasks that require in-context learning and precise retrieval, slowing their adoption for large-scale language modeling. In this work, we demonstrate that both the success and failure of SSMs in these domains can be explained by studying the role of the gating mechanism, a prevalent component in modern recurrent networks. Specifically, we show through theory and experiments that this gating mechanism causes SSMs to first learn an in-weights "memorization" solution, while delaying, or even preventing, convergence to a correct in-context learning solution. Importantly, this happens even in cases where there are no fundamental limitations due to the architecture or its memory capacity. On the other hand, we find that gating is often beneficial for improving generalization to long sequence lengths. Our results illuminate the crucial role of the gating mechanism in shaping both the training dynamics and generalization of SSMs, and provide a basis for understanding and improving linear-time models.

Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source corpus. The stored knowledge, however, is not always retrieved correctly. We study the eliciting side rather than the storing side: we use preference optimization, which learns from pairs of a preferred (chosen) and a dispreferred (rejected) response, so that the model elicits its stored knowledge more accurately. One proposed approach takes the model's own erroneous response as rejected and the gold answer as chosen, so as to suppress the error. When the target knowledge is partially known, however, most of these rejected responses are factually correct. Using direct preference optimization (DPO) then pushes down rejected responses that contain correct knowledge and differ from the chosen answer only in style, such as length and wording. We propose style-debiased DPO (SD-DPO), which scores whether the rejected response of each pair is factually correct, inverts the preference of such pairs, and weights them so that the learning signal due to differences in style cancels out as a whole. We first test whether, on top of EntiGraph, a representative storing-side method that runs CPT on text synthesized from the corpus, our method adds accuracy efficiently. On QuALITY, the reading-comprehension QA benchmark on which EntiGraph was evaluated, SD-DPO exceeds a baseline we CPT on EntiGraph's synthetic data from the same base model and evaluate with the same procedure. The training tokens this requires are a few dozen times fewer than the additional CPT needed for the same gain. For knowledge updating, the main goal of this work, we use AToKE, a knowledge-editing benchmark for facts that change over time. There, SD-DPO reaches an overall accuracy of 0.982 and answers with the new or the old fact according to the queried period.

Capturing hand motion and interaction forces is critical for interactive computing, VR, and high-fidelity tactile demonstrations for robot learning. We introduce a wrist-worn pressure-sensing wristband that recovers continuous full-hand pose and distributed contact force on a single wearable. The system consists of flexible capacitive sensor arrays around the wrist, which require no electrical skin contact, and a recurrent network that maps the resulting pressure signal to hand state. Our key insight is that muscle contraction and tendon displacement produce pressure patterns, which correlate strongly with hand pose and interaction force. To validate this, we collect synchronized recordings of wrist pressure, optical motion-capture hand pose, and tactile-glove interaction force, covering isolated finger motion, fingertip-force stress tests, and natural hand-object manipulation. On isolated single-user motion the wristband attains $4.6^\circ$ mean finger-joint MAE, and across four users manipulating everyday objects it estimates per-finger contact force at $R^2=0.57$, which an external pose signal brings up to $0.75$. We see the wristband as one node in a constellation of everyday wearables -- e.g. paired with an egocentric camera -- adding the contact force that vision cannot observe and taking over when the hand is occluded.

Human videos provide demonstrations of dexterous manipulation but lack robot-executable actions and tactile measurements. We present UniDex-ViTac, a framework that uses human-video-guided simulation to generate robot demonstrations paired with fingertip contact observations for training a deployable visuo-tactile policy. Object-specific residual reinforcement learning specialists adapt annotated human-object interaction references to a robotic arm-hand system. Their successful rollouts pair final robot action targets with robot-side fingertip contact observations. From 50 human demonstrations across ten objects, we collect 10,000 simulated trajectories to train a single Action Chunking with Transformers (ACT) based generalist. The policy combines point clouds, proprioception, and four binary contact signals encoded through fingertip labels and a separate token, without requiring human references or privileged object identity and pose at deployment. The contact-augmented configuration achieves 68.3% macro-average success in simulation, compared with 55.5% for the point-cloud-only baseline. Without real-robot demonstrations or policy fine-tuning, it succeeds in 73/110 physical trials (66.4%) across six seen and five unseen objects, compared with 60/110 (54.5%) for the baseline, an increase of 11.8 percentage points. These results support the feasibility of learning a unified visuo-tactile dexterous manipulation policy from video-guided simulated interactions. Project page: https://unidex-vitac.github.io/

Vision language action (VLA) policies continue to grow in parameter count, making deployment on resource-constrained robot platforms difficult. The central goal is to reduce the number of LLM-side parameters retained in the deployed policy while preserving downstream task performance. Our approach, AdaDE, adapts selected dense feed forward blocks into mixture of experts (MoE) layers and derives expert retention masks from router statistics during fine tuning. The Dense2MoE conversion preserves the original dense FFN function at initialization, so expert deactivation can start without a separate recovery stage. Instead of using a fixed shutdown rule, expert masks are updated dynamically from router usage statistics, with staged training and expert protection to avoid early collapse. With 40% of the LLM parameters deactivated, AdaDE retains 95.1% average success in LIBERO and 42.0% average success across all 50 RobotWin2.0 tasks. These results suggest that dense to MoE adaptation with dynamic expert deactivation is a practical direction for reducing active VLA model size without severe performance loss.

De-identified résumé screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leakage to declared languages. We investigate whether eliminating language fields resolves this leakage across nine open-weight models and 620 counterfactual résumés. By holding language attributes strictly identical, we isolate unstructured prose across five ethnocultural conditions and three cue-salience tiers. Target-group recovery averages 0.757 overall and saturates at 1.000 under high salience, demonstrating that non-language prose sustains demographic inference. Crucially, models diverge only under faint cues (0.086-0.690), establishing salience as an essential evaluation axis. Furthermore, pairwise LLM-as-a-judge outcomes are highly sensitive to evaluation design: forbidding ties yields an apparent selection-rate ratio of 0.39 alongside strong position and content effects, whereas permitting ties produces near-universal ties for most models ($\ge94\%$). Downstream scoring shows only very small between-condition differences, highlighting the need to distinguish demographic signals recoverable from résumé content from effects introduced by the evaluation protocol.

We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid scoring. Consider this example query: "what were last week's audience sizes"---the reference answer changes as the underlying data changes, so static references become outdated and standard LLM-as-a-judge pipelines cannot verify responses against a fixed ground truth. Our central contribution, ground-truth-as-code, encodes each expected answer as an executable reference function that recomputes the answer directly from live data at evaluation time, ensuring the reference remains consistent with the system it describes. We combine this with a factoid-level, format-agnostic judge that decomposes both the agent's response and the computed ground truth into atomic claims and scores precision, recall, and accuracy over them, irrespective of the response format (prose, list, table, HTML, etc.). The approach is applicable to agents whose expected outputs can be expressed as executable data computations. We validate the framework through a human--LLM agreement study on an internally developed machine learning skill deployed in production, using a synthetic database constructed to reproduce production schemas and entity relationships. Relative to a natural-language ground-truth baseline, our method achieves a 29% improvement in the Matthews Correlation Coefficient (MCC)---a class-balanced measure of agreement between expert annotators and LLM-as-a-judge predictions---and a 16% reduction in token consumption per test case, while a self-directed baseline lacking explicit ground truth is anti-correlated with human judgment. Agents that perform multi-source data integration and computation over non-stationary data are routinely deployed in industry; we propose ground-truth-as-code as a practical methodology for their evaluation.

Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe performance degradation under a coupled dual-drift paradigm: visual domain drift from cross-spatial-resolution mismatches and spectral variations, alongside textual logic drift from unconstrained, variable user-input granularities. To mitigate these bottlenecks, this paper establishes the first cross-domain RRSIS benchmark, designated as the Vaihingen-Potsdam Referring (VPRef) dataset, comprising 46,972 language-image-annotation triplets organized into a three-tier linguistic hierarchy. Building upon this benchmark, we develop a tailored parameter-efficient domain adaptation baseline anchored on the Segment Anything Model (SAM3) via Low-Rank Adaptation (LoRA). Our framework counteracts visual distribution discrepancies through pseudo-label-driven self-training and addresses textual logic drift via random multi-granularity text prompt mixing. Crucially, the distribution of empirical metrics across ablative variants suggests a potential decoupling between cross-modal semantic robustification and visual domain alignment, demonstrating that linguistic variance drives fine-grained semantic invariance while pseudo-label propagation governs macro-scale spatial grid alignment. Extensive benchmarks demonstrate the proposed framework achieves superior cross-domain segmentation boundaries while modifying merely 1.08\% of the foundational parameter footprint, establishing a robust baseline for future multi-modal remote sensing domain adaptation research. The dataset and code will be available at https://github.com/quanweiliu/VPRef.

Privileged on-policy distillation improves multimodal reasoning by allowing a teacher to evaluate student trajectories using rich, training-only visual evidence. Both models score these trajectories while conditioning on the same student-generated prefix. When a student misinterprets an image early in a response, this accumulating erroneous rationale eventually pulls the teacher away from its visual evidence. The teacher and student converge on the same hallucination, causing standard cross-model supervision to collapse precisely where correction is most needed. We find that the teacher's visual corrective preference is not lost under this misleading agreement. Comparing the predictions of the identical teacher given the real image and a visual null reveals that the privileged evidence still pushes the model toward the correct interpretation. We introduce OPD-Aha, which reconstructs the distillation target directly from this isolated visual preference rather than relying on the fragile teacher-student discrepancy. This reconstructed target aggressively suppresses continuations that contradict the image. Trained with this objective, students learn to naturally interrupt their own flawed reasoning with reflection tokens such as wait and actually. After reflection, subsequent generation relies less on the accumulated erroneous text and more on the visual evidence. Correcting these trajectories mid-generation fundamentally alters the reasoning process, yielding broad and consistent improvements across diverse fine-grained perception and complex multimodal reasoning benchmarks. Our code and models are available at https://github.com/Echochef/OPD-Aha.

Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation through iterative unmasking. However, dLLMs typically require many steps before token confidence reaches the decoding threshold, resulting in inefficient inference even with block-wise KV caching. To accelerate dLLM inference, we for the first time propose an "early-bird (EB)" decoding framework, motivated by the observation that tokens with similarly low entropy tend to cluster and can be jointly decoded earlier, before reaching the confidence threshold. In particular, our EB-Decode framework integrates two key enablers: (1) a learnable network that adaptively groups tokens with similar uncertainty into variable-length blocks, rather than relying on fixed block sizes; (2) a position-aware sampler that learns to unmask tokens in parallel using fewer decoding steps within predicted variable-length blocks. Both components are developed without modifying pretrained dLLM weights and can therefore be directly deployed as plug-ins during serving, with negligible training and inference overhead. Extensive experiments across three models and four benchmarks consistently validate our observation and the effectiveness of EB-Decode, achieving 3.53-18.76$\times$ higher throughput than the vanilla decoding method and up to 1.58$\times$ higher throughput over the strongest baseline, Fast-dLLM, with comparable accuracy.

State-of-the-art visual locomotion controllers are increasingly capable at handling complex visual environments, making evaluating their real-world performance before deployment increasingly difficult. This work intends to narrow this train/evaluation gap by developing a collection of hyper-photo-realistic, closed-loop evaluation environments - The Neverwhere Benchmark Suite - comprised of over sixty 3D Gaussian Splatting reconstructions of urban indoor and outdoor scenes. Our goal is to encourage large-scale and reproducible robot evaluation by making it easier to create and integrate Gaussian splats-based reconstructions into simulated continuous testing setups. We also underscore the potential pitfalls of relying exclusively on 3D Gaussian-generated data for training, by providing policy checkpoints trained over multiple Neverwhere scenes and their performance when evaluated in novel scenes. Our analysis illustrates the necessity of sourcing diverse data to ensure performance. Code and data are available on the project page: https://ziyc.github.io/neverwhere-bench/.

Collecting high-quality robot data for contact-rich manipulation tasks is essential for enabling robots to acquire real-world skills. However, existing data collection solutions often lack the capability to obtain stable and high-frequency tactile feedback, limiting their effectiveness in contact-rich manipulation scenarios. In this work, we propose a versatile teleoperation system with tactile-driven assistance to enable high-frequency and stable contact-rich manipulation. The proposed XRoboToolKit-T teleoperation system incorporates a tactile-informed force control architecture, designed to ensure both stable and precise force control in contact-rich manipulation during teleoperation. The stabilizer haptic module rapidly analyzes the normal force distribution and infers pseudo shear force, enabling real-time tactile-based assistance during manipulation. The refiner haptic module integrates a vision-language-action model to predict and refine manipulation actions based on tactile sensing data and task descriptions. We apply the proposed teleoperation system to challenging contact-rich manipulation tasks, including grasping a deformable rubber pipette for liquid transfer and inserting a medical syringe into a vascular training pad, to demonstrate the effectiveness of tactile-informed force control. Furthermore, the system achieves higher data collection efficiency and improved manipulation stability compared to state-of-the-art teleoperation without tactile assistance.

Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the social scientific toolkit. However, LLMs are ultimately black boxes based on deep neural networks which limits their value for social science. This is because of a lack of (i) interpretability: i.e. the ability to assign clear mechanisms driving observed behavior; and a lack of (ii) steerability: i.e. the ability to mute or amplify specific theoretically meaningful mechanisms of action to drive specific model behavior. Here, we demonstrate how the black box could be opened up to further enrich LLM-based simulations. Specifically, we compare three types of methods: (1) prompt-based manipulation, (2) SAE-derived feature steering, and (3) probe-based direction steering and examine their utility for LLM-based social scientific simulations. We do so by interpreting and steering two foundational components of human behaviors, namely preferences (risk attitudes, altruism) and capabilities (divergent creativity, product innovation), operationalized using four classic economic and creative tasks implemented as natural-language interactions. Overall, our results show that SAE- and probe-based techniques often outperform basic prompt-based methods for steering LLM agents, although this advantage depends on the specific prompting strategy involved. Together, SAEs and probes constitute an effective pipeline for social scientists seeking to interpret and steer agents in social simulations: SAEs decompose agents' internal representations into human-readable features, after which probes can reliably shift agents' behaviors in specified directions. We discuss implications of these methods for future work using LLM agents for social scientific simulations.

Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual domain presents limitations for tasks requiring direct manipulation of visual representations. Recent efforts augment multimodal LLMs with external visual expert tools such as depth estimation or object detection modules, but these remain fundamentally limited by their reliance on narrow, rigid operations that cannot flexibly generate or transform visual content. We propose ReImaGin, which leverages image generation models as a flexible visual reasoning mechanism for multimodal LLMs: unlike fixed-function tools, they accept natural language commands and can perform open-ended visual operations, like removing an occlusion or generating a floorplan from multiple disjoint views of a room. Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25\%, demonstrating the advantage of flexible, generative visual reasoning.

Humanoid robots often execute motion commands through whole-body controllers (WBCs) that track targets while maintaining balance and stability. However, most WBCs are blind to scene geometry, which can lead to collisions from imperfect target motions that are geometrically unsafe due to perception, planning, or teleoperation errors. We propose RECAL, a Robot--Environment Cross-Attention Layer that wraps a blind WBC to trade off target tracking against collision avoidance using external scene geometry. RECAL supports collision-aware tracking of floating-base and end-effector commands, including collision avoidance for held objects. It represents the robot, held objects, and environment as point clouds, using cross-attention between robot/object points and the environment to produce geometry-aware control features. In simulation, RECAL improves collision avoidance while preserving target-tracking performance across frozen-arm and adaptive-arm locomotion, object-carrying, and standing-manipulation scenarios relative to alternative geometry-aware WBC architectures. We further demonstrate the controller on a real Digit V3 humanoid robot.

We introduce ParsHate, a manually annotated dataset of 10,000 Persian tweets spanning 2013-2022, representing the first decade-long benchmark for hate speech detection in Persian. The dataset contains 31% hateful content and supports both hate detection and multi-label fine-grained target identification across seven structured target categories. ParsHate also distinguishes explicit and implicit hate, marks explicit and implicit targets, and provides span-level rationales. Data collection combines random and score-stratified temporal sampling to reduce keyword-driven bias while preserving natural label distributions. Applying SOTA models for Persian hate-speech detection on ParsHate shows moderate performance (79% F1), especially with samples from earlier years, and low performance with target identification (25.5% macro-F1). This emphasizes the diverse sampling of hate speech in ParsHate and its challenging nature that requires more advanced methods for better performance. Dataset is made publicly available.

Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embedding table, allocate bits by module sensitivity, prefer a ranking-aware objective over weight reconstruction -- was carried into LLM quantization largely intact. We test that advice on retrieval embedders directly, quantizing five checkpoints from four architecture families across a grid of bit widths and group sizes, and isolating the embedding, attention and feed-forward blocks at each width. Every heuristic fails to transfer as stated. The embedding table never emerges as the dominant isolated protection priority in any family, despite being the largest tensor in several of them. Module sensitivity does not survive as a transferable ordering: at INT4/g16 the spread between modules is too small to allocate against, at INT3 the ordering becomes family-dependent and joint damage stops being the sum of its parts, and at INT2 comparable reconstruction error accompanies retention ranging from 1.3 to 65.9 percent of full precision. A cheap reconstruction proxy is useful for screening uniform bit widths but substantially less reliable for choosing which tensors to protect; its apparent strength across the whole grid is a range-extension artifact. A distilled 109M student at INT3 holds 78.04 NDCG@10 in 68.4 MB and dominates the extreme-PTQ arm of its own 0.6B teacher, 297.9 MB at 64.46, on both size and quality -- but only inside the task it was distilled for. Sizes are byte counts of files that exist rather than arithmetic estimates, and the measurement repository carries the byte provenance for every one of them.

In thin-film lithium niobate Mach-Zehnder modulators, half-wave voltage and bandwidth are tied to the same design parameters; hence, improving one usually costs the other. Several methods have been pursued in the past to alleviate this tradeoff. Specifically, the bias voltage can be reduced through non-centered placement of optical waveguides with respect to electrodes, slow-wave optical gratings, and high-permittivity cladding layers. Bandwidth can be enhanced through implementing periodic segmented electrodes and exploiting low-permittivity bottom cladding and substrate materials. The objective of this work is to study the augmentative impact of these methods. We pursue a rigorous modeling and optimization approach to achieve this objective, estimate the impact of each augmentation, and evaluate the ultimate performance of TFLN MZMs based on these methods. It is shown that a co-designed structure that incorporates all these enhancing methods can attain a drive voltage of 0.84 V and a modulation bandwidth of almost 220 GHz.

Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally requires keeping earlier generated text in context. We ask whether a dLLM can instead continue reasoning after that text is cleared, using only a fixed-size carried state. We implement this state as a small number of register tokens: dedicated fixed-position tokens whose continuous hidden states are trained to carry reasoning progress across generation chunks. We post-train dLLMs to decode a chunk of text, clear it while preserving the register values, and continue decoding from the prompt and carried state. In our main comparisons on LLaDA and Dream, registers outperform discrete-text carry on every benchmark, with gains of up to 8.5 points on math and 19.5 points on code. Registers are especially effective for bounded code generation, where correct programs usually span several chunks. Finally, registers can be further refined with reinforcement learning on long-horizon reasoning tasks.

Wireless edge caching networks typically consist of many independent Base Stations (BSs), each facing its own request rate and content popularity profile. Training a Reinforcement Learning (RL) caching agent from scratch at every BS forces each agent to relearn, through slow trial and error, a decision problem that is structurally identical across the network. Meta-reinforcement learning removes this redundancy by learning a shared initialization that adapts to any BS in a few local updates; however, meta-training itself becomes the bottleneck at scale: the meta-gradient must be estimated from a small subset of BSs at each meta-iteration, and sampling this subset uniformly at random yields a high-variance estimate, an issue existing meta-RL caching frameworks leave unaddressed. This paper proposes a meta-reinforcement learning framework for caching across independent, non-overlapping BSs that directly targets this bottleneck. Each BS runs a local Proximal Policy Optimization (PPO) agent, formulated as a Semi-Markov Decision Process (SMDP) over content popularity, size, lifetime, and importance, while a shared meta-policy is learned via a Model-Agnostic Meta-Learning (MAML)-style loop. To scale meta-training and accelerate convergence, we introduce gradient-based clustering, which groups BSs by local gradient similarity and draws from every cluster, in proportion to its size, at each meta-iteration. We prove, via an Analysis of Variance (ANOVA)-style decomposition of gradient variance, that this strategy yields a strictly lower-variance meta-gradient estimator than uniform random sampling under BS heterogeneity.

Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous droplet transport through confined geometries of varying complexity remains an open challenge. Droplets exhibit contact-angle hysteresis, deformability, and capillary pinning, which make their response to actuation nonlinear and history dependent, that classical controllers and pre-programmed trajectories cannot cope in multi-turn environments. Here we demonstrate autonomous navigation of a liquid droplet through geometries of increasing complexity on a gravity driven (Labyrinth) platform using model-based reinforcement learning. A thin silicone oil film reduces contact-line pinning while two-axis tilt supplies the gravitational driving force, and an overhead camera tracks the droplet in real time. An offline-trained policy discovers effective tilt strategies from limited physical interaction data, without simulation or analytical droplet models. The system operates under partial observability, as oil-film thickness, instantaneous contact angle, and droplet deformation state remain hidden from the controller. Despite these challenges, the learned policy achieves reliable navigation across straight, right-angle, and curved-arc paths, including outside-corner geometries. We further demonstrate that a policy trained on a simpler geometry transfers to complex ones, succeeding zero-shot on right-angle and staircase paths and reaching full success on a curved arc with a fifth of the training data. The findings suggest promising avenues for enabling droplet based microfluidic systems to serve as intelligent chemical laboratories.

When foundation models describe people, recent work in AI fairness, accessibility, and ethics recommends avoiding inferred identity labels (e.g., "she", "his") in favor of seemingly "objective" physical descriptions (e.g., "short hair", "a defined jawline"). Yet whether such descriptive language achieves gender-neutral communication remains an open empirical question. To study this, we introduce GAPA (Gender Associations of Physical Attributes), a dataset of 316 common physical attributes drawn from diverse sources, paired with 14,706 gender-association ratings from 304 US-based annotators. Results show that physical descriptions carry structured and graded gender associations among readers, with more consistent and distinctive associations for women and men than for non-binary identities. Next, we evaluate 16 LLMs across model families, sizes, and post-training variants against human ratings. The models partially recover human associations but exhibit systematic alignment biases, including compressed rating distributions, weaker alignment for associations with men, and asymmetric abstention that disproportionately targets the non-binary category. Finally, we release the best-performing proxy model trained to predict humans' gender associations of descriptive language and demonstrate its utility through a sociolinguistic analysis of character descriptions in LitBank. Together, our findings provide the first empirical evidence that seemingly "objective" physical descriptions can retain systematic gender associations in human interpretation, and uncover systematic patterns of model-human misalignment. This challenges the assumption that replacing explicit gender labels with physical descriptions necessarily yields gender-neutral communication, and highlights downstream challenges in using such descriptions to communicate subjective identity categories in human-AI interaction.

This paper presents Auto-HSI, a method for generating personalized human-swarm interaction (HSI) interfaces on demand. The objective is to enable untrained operators to use natural language descriptions and gesture demonstrations to explain how they want the robots to collectively behave in response to their gestures. Based on these inputs, the code should automatically be generated for personalized state machines that will control the robots as desired, in response to the desired gesture inputs. In the developed Auto-HSI prototype, the generated code produces a personalized interface for centralized control using one- and two-handed gestures, enabling a user to teleoperate the robots' motion, formation shape, and shape deformation. We test the gesture tracking and code generation components of Auto-HSI against performance benchmarks. We then test the full Auto-HSI prototype in ``live'' operation experiments, in which real human operators centrally control 50 simulated robots in a physics-based simulator, under nominal and noisy conditions. In these experiments, robots are teleoperated to: score a goal, traverse a maze that requires shape deformation, and score two simultaneous goals by splitting into two groups. We also demonstrate a real human operator making live updates to their personalized Auto-HSI interface during operation (in simulation). Finally, we demonstrate live operation of real robots.

Machine translation systems are periodically upgraded to stronger models, but the available preference signal is human post-edits of an older system's outputs, which the newer model may already surpass. Moreover, collecting fresh post-edits for every new model is prohibitively expensive. We call this the Stale Preference problem. Standard DPO can fail in this setting: it may increase the likelihood of inferior post-edits, erode the model's existing quality, and fail to provide the per-token control needed to correct localized errors. We introduce StalePO, an objective derived from three requirements this regime imposes. Likelihood movement must be downward on both responses, the policy must be anchored to its own base response, and the KL constraint must apply at the token level. These requirements are jointly necessary. In ablations, each mechanism in isolation leaves the model's performance indistinguishable from the base model, and only their combination converts stale feedback into gains. On English-to-Hindi and English-to-Turkish localization data, StalePO improves the fraction of segments passing all LLM-as-judge MQM quality checks by 14.9 and 4.6 percentage points, respectively, with gains concentrated on style and fluency. A human evaluation under the same framework confirms these gains on English-to-Hindi, raising the fraction of segments passing all seven human checks by 13.8 percentage points.

We present ManiSkillFormer, a neuro-symbolic framework for demonstration-free and compositional robotic manipulation. Instead of learning end-to-end visuomotor policies, ManiSkillFormer introduces task-conditioned geometric contracts that explicitly structure the interface between perception and action. Each manipulation skill declares the semantic geometric primitives required for execution, such as object keypoints and surface normals. Building on human-defined skill structures, LLM agents generate these contracts and corresponding motion templates for different objects and task contexts. These contracts guide the perception module to ground task-relevant 3D primitives from observations, which are then used to instantiate reusable motion templates stored in a skill library. We evaluate ManiSkillFormer on Galaxea R1-Lite dual-arm robot across three settings: zero-shot pick-and-place over 8 object categories with 30 different instances, functional manipulation tasks including unscrewing, pouring, pressing, and folding, and 3 long-horizon tasks. ManiSkillFormer achieves higher average success rates than the evaluated baselines and two ablated pipelines: 88.24% for demonstration-free pick-and-place, 75.00% average success on functional manipulation and 50--80% completion rates across the long-horizon tasks. These results show that our design enables composable and reusable manipulation across objects and tasks without per-object policy fine-tuning or additional robot demonstrations.

Dexterous grasping is usually conducted for specific tasks, leading to heterogeneous constraints such as specific approach directions, desired contact regions, specified wrist trajectories, and functional hand poses. Our previous work, GraspXL, achieves scalable grasping motion synthesis for diverse objects and hand morphologies, while lacking controllability for synthesis under such various task-driven constraints. In this paper, we propose ConGraspXL, which extends GraspXL with controllable constraint-conditioned grasp motion synthesis that accommodates diverse task-driven constraints and their combinations. We introduce a hierarchical constraint formulation, enable flexible constraint composition with a masked residual interface, and improve control precision with dynamic hand centers and feed-forward wrist guidance. Without losing the strong generalization capabilities of GraspXL, ConGraspXL enables precise and flexible controllability for various individual constraints and their combinations, providing a plug-and-play low-level grasp controller for downstream applications such as whole-body grasp completion, functional grasping, and human-motion imitation.

Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings, safety failures may emerge only after multiple turns, yet existing evaluations often reduce agent behavior to task or attack success, obscuring whether an agent acts, refuses, or remains appropriately calibrated as the interaction evolves. We introduce Blindspot, a benchmark for trajectory-level safety calibration of long-horizon tool-using agents. Blindspot evaluates complete user-agent-environment trajectories through adaptive adversarial interaction, stateful tool execution, and execution-grounded adjudication. Its current instantiation contains 22 attack families and 35 scenarios across seven domains, yielding more than 2,500 long-horizon trajectories with an average interaction length of 14.7 turns. Each trajectory is assigned one of five outcomes: Safe Completion, Correct Refusal, Unsafe Completion, Over-Refusal, or Indeterminate. Unlike fixed attack datasets, Blindspot is an extensible live-simulation framework in which attacks, scenarios, tools, policies, domains, and agent configurations can be added without redesigning the evaluation pipeline. We evaluate 13 proprietary and open-weight LLMs using eight metrics covering unsafe completion, appropriate refusal, benign utility, over-refusal, repeated-run robustness, and post-refusal failure. Preliminary results reveal substantial differences in safety-utility calibration across models and show that failures can emerge only after several initially safe interaction steps. These findings motivate treating agent safety as a trajectory-level property rather than a single-turn or binary success criterion.

Medical knowledge evolves continuously, whereas the parametric knowledge encoded in large language models (LLMs) is fixed at training time. External retrieval, including retrieval-augmented generation (RAG), can provide access to newly available evidence, but retrieved information may be irrelevant, incomplete, or conflicting. As a result, external retrieval can in turn degrade the factual accuracy and evidence grounding of LLM outputs. To address this challenge, we propose \textbf{CLEAR}, an agentic framework for cross-source evidence adjudication in LLMs in medicine. CLEAR independently generates candidate answers from three complementary pathways---parametric knowledge, locally curated corpora, and dynamically retrieved evidence---reflecting three common sources of information available to LLMs. An aggregation verifier jointly evaluates the candidates, supporting evidence, provenance, and source-quality information to identify agreement and conflict across sources. An adjudication module then determines whether the current conclusion should be preserved or revised through complementary override-guard and challenge-audit mechanisms, while unresolved conflicts trigger targeted follow-up search and re-adjudication.

Domain Randomization (DR) has been widely used to overcome the sim-to-real gap by training a controller on a distribution of simulated environments via reinforcement learning. While DR can achieve robust performance simply using controllers synthesized via policy gradient (PG) methods, the optimization landscape is not well understood, even in the case of linear quadratic regulator (LQR) objectives. To this end, we first study PG of domain randomized LQR over history-dependent policy classes, such as finite impulse response controllers, as they can extend the possibilities of simultaneous stabilization. Second, to find such a stabilizing controller, we propose a curriculum learning based algorithm which gradually expands the memory of the controller. Finally, we show that PG with the proposed algorithm converges globally to the minimizer of a sample average approximation of the DR objective under suitable bounds on the heterogeneity of environments. Empirical results support our findings and highlight promising directions for future work, including nonlinear domain-randomized control.

The ongoing replacement of synchronous generation by inverter-based resources (IBRs) introduces fast converter control dynamics whose characteristic frequencies extend beyond the classical electromechanical band. Conventional small-signal stability tools are commonly formulated in the phasor domain, representing electrical quantities as slowly varying phasors at the fundamental frequency, and therefore cannot resolve the sub-synchronous and converter-driven dynamics that increasingly arise in operation. Electromagnetic Transient (EMT) modeling captures these dynamics, but established EMT simulators produce time-domain waveforms rather than the modal indicators (eigenvalues, damping ratios, and participation factors) needed to assess stability risk. This paper presents EMT-SSA, an integrated tool suite for EMT-level small-signal analysis of IBR-rich power systems. From a standard PSS/E system snapshot (.raw/.dyr), it converts the model into an EMT representation with enhanced fidelity, solves an extended power flow for the steady-state equilibrium points of both the network and the device controllers, and linearizes a full-order EMT model to form the system state matrix, from which it produces eigenvalues, oscillation modes, and participation factor analysis results over a device library spanning synchronous generators, grid-following and grid-forming inverters, transmission lines, and loads. The EMT-SSA tool suite identifies poorly damped or unstable modes and attributes them to specific devices. The tool is demonstrated on the Kundur two-area system, with its modal results benchmarked against PSS/E NEVA.

Large language models are increasingly deployed as interacting agents, making the persistence of their action policies across repeated interaction critical for reliable multi-agent operation. We investigate whether and how agent-generated, non-binding pre-play communication ("cheap talk") increases such persistence in four open-weight 7-9B-parameter LLMs. Our experiments span four repeated two-player games -- Prisoner's Dilemma, Snowdrift, Stag Hunt, and Harmony -- with incentive structures ranging from strategic conflict to alignment, each presented in six contexts. We observe unstable trajectories in all four games, although their prevalence and magnitude depend strongly on model and context. Across models, games, and contexts, cheap talk is predominantly stabilizing, with five corrected reversals concentrated in social or team framings; effects vary substantially by model and context. Controlled current-message interventions identify two separable output-level channels in Qwen: reduced action uncertainty and less between-round drift in action probabilities. Matched history-by-message counterfactuals further show that recent partner behavior conditions how mutual-benefit versus self-prioritizing language affects policy persistence. Finally, in Prisoner's Dilemma, we identify in Qwen and Falcon a history-balanced policy-content direction in late transformer layers; projecting out this direction increases realized switching during closed-loop play, demonstrating that complete trajectories are causally sensitive to this component. Together, these findings show that cheap talk can make individual trajectories more persistent across diverse incentive structures, while revealing that the magnitude and mechanisms of stabilization are model- and history-dependent.

Large language model (LLM) agents increasingly interleave natural language reasoning with external tools such as web search and code execution. These tool-use policies are often optimized via reinforcement learning (RL), which can amplify spurious correlations in the training data. In this work, we study when and why RL-trained agents learn shortcut tool-selection policies: invoking tools based on superficial prompt cues rather than genuine task requirements. We construct controlled synthetic environments combining factual question answering and mathematical reasoning tasks, and inject cues that are strongly correlated with specific tools during training but causally irrelevant to tool necessity. Across counterfactual evaluations where cues are present but the associated tools are not required, agents exhibit substantial shortcut behavior, with spurious tool invocation rates increasing by up to 39 percent. However, shortcut formation is not universal: across the conditions we test, it arises only when the agent has already learned to use the target tool reliably, suggesting that task competence, rather than dataset imbalance alone, is a key factor in shortcut learning. A swapped-cue analysis further shows that semantic alignment between cues and tools substantially amplifies this effect. To mitigate these failures, we introduce a dense, decision-level reward in which an LLM judge evaluates the necessity of each tool call. This tool-necessity reward effectively suppresses cue-driven tool use while preserving task performance, providing a practical approach to improving the robustness of LLM agent tool-use policies.

Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify model weights via gradient ascent and its advances. While effective on certain benchmarks, these weight-based approaches exhibit a sharp forget-utility trade-off, where stronger forgetting of target knowledge can degrade model utility, and unlearned knowledge may reappear under post-unlearning fine-tuning or prompt attacks. We propose ARIA (autoencoder-gated inference-time unlearning), a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state. ARIA uses sparse autoencoder (SAE) latents to train a lightweight linear detector, then applies an interpretable intervention on triggered states with negligible test-time overhead. Empirical evaluations on TOFU, R-TOFU, and WMDP show that ARIA improves the forget-retain trade-off over weight-based baselines across both a thinking model (DeepSeek-R1-Distilled-Qwen-1.5B) and an instruction model (Gemma-3-1B-it), e.g., reducing WMDP-cyber forget-set accuracy significantly while keeping MMLU within 1% of the pre-unlearning model. We further introduce three post-unlearning adversarial attacks targeting weight-space and decoding-space recovery, and find that ARIA remains robust under all three, with forgetting changing by less than 1% under attack. A feature-level case study leveraging the interpretability of ARIA suggests that some retain degradation may reflect response styles underlying the unlearning data rather than leakage of the targeted knowledge itself, highlighting a potential source of bias in unlearning task construction.

Autonomous soft-tissue cancer surgery has been limited to interventions on organ surfaces, because current systems cannot perceive and adapt to anatomy once it deforms or is cut. We introduce the first vision-guided autonomous system capable of performing complete tumor resections for partial nephrectomy. Our system integrates conditional occupancy networks, trained entirely in a physics-based simulation, that infer full 3-D anatomy (tumor, margin tissue, and kidney) from single-view partial point clouds. These occupancy networks maintain intraoperative tracking even as tissue is cut and deformed, enabling adaptive planning and execution. The surgical platform combines a depth camera for capturing surface point clouds, dual robotic arms for electrosurgical cutting and vacuum-based tissue manipulation, and an autonomous control strategy for tumor resection. In patient-derived hydrogel phantoms under an open partial nephrectomy setting, the robot performed eight consecutive autonomous tumor resections comprising 77 electrosurgical cuts, with all cuts achieving negative surgical margins and 1.61 $\pm$ 0.48 mm mean absolute margin error. This work demonstrates, for the first time, a foundation for supervised autonomous closed-loop, imaging-driven, margin-negative tumor removal in phantoms.

We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We propose CRN v2, a lightweight logit-level correction module (~34M trainable parameters, 0.73% of the 4.65B text module) that sits atop a fully frozen Gemma 4 E2B model. The base model is never updated; only the correction module learns, via supervised fine-tuning followed by reference-free DPO on 83,400 error-correction pairs. On a 60-question domain exam (CEHRI: Certified Human-Robot Intelligence, covering facts, arithmetic, and implicit-goal reasoning), CRN v2 corrects 53.3% of base-model errors (reworded variant: 43.3%) while showing no degradation on tested capability benchmarks (MMLU/BoolQ N=200; car-wash N=8). A LoRA baseline at the matched CRN v1 budget (6.6M params, rank 19) achieves 83.3% correction but suffers 30-75% capability loss on the same benchmarks -- the correction-capability tradeoff. An ablation shows that the KL preservation term (lambda=0.1) is critical: lowering it to 0.01 degrades correction to 35.0%. A hidden-state injection variant at earlier layers (1.6M params, SFT-only) reaches 50.0%/55.8% but does not exceed logit correction; shallower injection (layer 4) drops to 30.0%/28.3%; multi-depth logit correction (~35M) reaches only 40%; and longer training (5,000 SFT + 2,000 DPO) stays at 53.3% -- none of the alternative configurations we tested exceeded the rank-128 logit result, consistent with a best-achieved result of ~53% rather than a floor. This is a study of a design principle (frozen base + logit correction + KL anchoring), not a claim of architectural novelty. All code, main-result weights, and evaluation scripts are released (deep variant as code only -- no trained deep checkpoints).

Safe control of humanoid robots remains challenging due to their high-dimensional dynamics, contact-rich interactions, and sensitivity to disturbances. Although reinforcement learning has enabled effective locomotion and motion tracking, learned policies can still generate unsafe actions that lead to instability or falls. In this work, we propose residual reinforcement learning as an implicit safety-filtering mechanism for safe humanoid control. Instead of relying on a single nominal policy to simultaneously balance performance, safety, and robustness, we decouple performance and safety. The nominal policy focuses solely on task performance, while a residual policy learns safety corrections. This decoupling leads to a better performance--safety Pareto trade-off and avoids the need for careful tuning of multiple competing reward terms within a single policy training. We show that the residual policy can act as an implicit safety filter.

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy Optimization (BPO), a critic-free method derived from Policy Mirror Descent (PMD). For autoregressive generation with terminal rewards, BPO uses the Bellman equations to reformulate PMD as a trajectory-level objective. The reformulation avoids estimating state values at intermediate states. We prove that it has the same unique optimal solution as the original PMD objective. We derive the practical BPO loss by approximating this objective. Its mismatch-correction weight is a smoothed ratio of complementary token probabilities. Experiments on mathematical reasoning benchmarks demonstrate the effectiveness of BPO.

Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colosseum, a model-agnostic harness for allocating inference across research in mathematics and theoretical computer science. Colosseum explores alternative strategies before proof construction, uses a readiness gate to decide when a route is mature enough to decompose, represents the proof plan as interdependent section-level subproblems, and routes verifier findings back to the affected part of the argument. Across these stages, it generates candidates in parallel, attacks them with targeted falsification, and combines candidates and their critiques into a single research artifact through overlapping random-sample tree aggregation. The Colosseum workflow has been integrated into Google Antigravity's Teamwork framework as the Long Proof pattern. We demonstrate the capabilities of Colosseum through open-ended research and evaluations on theorem-proving and competitive programming benchmarks. Using Colosseum with Gemini 3.1 Pro, we obtain several new results that address open problems arising from papers published at top venues such as FOCS and JMLR. On TCS-Bench, a benchmark of research-level theorem-proving tasks drawn from papers published at FOCS, STOC, and SODA, Colosseum achieves 71.0% accuracy using Gemini 3.1 Pro and Gemini 3.7 Flash. In a separate Codeforces evaluation using Gemini 3.1 Pro, the proof-oriented pipeline with execution feedback solves 218 of 222 problems.

Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and caps the library size. Retrieval pipelines move the selection out of the context, but also out of the agent's capability. We show that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context. Gavel (Glance And Verdict from a frozen LLM) reads it in two steps. A glance projects the task's and each skill's mid-layer states through the two maps, the only parameters trained, and scores the full library against compact per-skill banks that one forward pass builds at installation. A verdict then resumes the shortlisted skills' forward passes and reads the model's own likelihood and yes/no judgment, fused with the glance as a product of experts. Trained once, Gavel transfers zero-shot to three public benchmarks and SkillTraj, our new benchmark of 372 simulated agent trajectories. On Qwen3-32B it outperforms progressive disclosure and retrieve-and-rerank pipelines that add 1.2B to 16B external parameters, by up to 13.4 points on written tasks and up to 21.9 when the need for a skill arises mid-rollout. Routing accuracy improves as the backbone does, and in a bash-agent harness the same 32B triggers the correct skill on Skill-Use more often than far larger frontier models running in Codex.

Mobile manipulators deployed across many rooms and visits should improve with experience: after discovering that a cabinet is locked or finding an object in a drawer, the robot should reuse that knowledge rather than start each task from scratch. Yet today's robots often treat each task as new: compact scene representations omit interaction-derived knowledge, raw video histories are difficult to query, and VLM planners reason at inference time without persistently updating what the robot knows. We present MessyMem, a persistent memory system that enables mobile manipulators to learn from experience and reuse that knowledge across future tasks. It maintains a spatially grounded 3D scene graph of objects and locations, augments it with properties and outcomes learned through interaction, and links visual observations for fine-grained recall. We evaluate MessyMem in simulation and on a real mobile manipulator. In a continuous 25-task simulation spanning over 3 hours, MessyMem achieves 80.0% task progress, outperforming the strongest ablation by 14.8 percentage points and the strongest external baseline by 28.9 points, while retrieving task-relevant evidence from thousands of stored keyframes and over an hour into the past.

Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this evolution as a functional geometry, decomposing learned updates into parallel and perpendicular components. Across pretrained models, we find substantial parallel components beyond the residual identity path. We then apply the decomposition in two spaces: to attention and MLP updates relative to the hidden state, and to attention value aggregation relative to the current token's value. Targeted edits reveal a strongly space-dependent asymmetry: exclude-self value-space parallel manipulation is markedly more robust than residual-space and perpendicular counterparts, preserving the direct self message while scaling only the non-self aggregate. The same decomposition gives a component-resolved description of compression-induced update error: perpendicular error separates compression methods more clearly than parallel error. Extensive experiments further demonstrate that full-aggregate parallel suppression during from-scratch pretraining lowers validation-loss trajectories and improves downstream averages, with the value-space variant strongest. Together, these results connect representation geometry to editing robustness, compression diagnosis, and training-time intervention. Code is available in the \href{https://github.com/Shwai-He/Transformer-Geometry}{project repository}.

Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the next frontier is a further transition: from solving and acting within problems specified by humans to participating in the process by which new problems, representations, explanations, and knowledge are created. We refer to this capability as Discovery Intelligence. We formulate Discovery Foundation Models (DFMs) as general-purpose model systems for open-ended discovery. A DFM operates over a revisable research state and supports seven coupled capabilities spanning problem discovery, formulation, representation construction, hypothesis formation, intervention, evidence-grounded revision, and continual discovery improvement. We instantiate this framework with Zetema, which couples explicit research-state dynamics, verification and experimental gating, external grounding, and cross-task Discovery Skill evolution. We further ground the framework with GALILEO, a real therapeutic-discovery system in which Dry-Lab reasoning, robotic and hands-on Wet-Lab experimentation, external biological evidence, and iterative hypothesis and design revision form a closed physical discovery loop. We then formulate a unified approach to capability formation and process-centered evaluation, enabling discovery behavior to be trained, improved, and measured beyond final-answer performance. Together, these components establish discovery as a learnable, executable, and evaluable capability of foundation-model systems. We view this shift as a broader progression in intelligence scaling: from learning over existing knowledge, to learning from action outcomes, and ultimately to participating in the construction, testing, and revision of the structures through which new knowledge is discovered. Code: https://github.com/Gen-Verse/DFM-Plans

Vision-language-action policies are typically evaluated one perturbation at a time, providing a useful diagnosis of their sensitivity to individual distribution shifts. Real-world deployment, however, may involve several shifts simultaneously, and it remains unclear how these individual robustness measurements compose. We ask whether compound robustness can be inferred from single-axis evaluations. We introduce LIBERO-CTRL, a six-axis benchmark that pairs each initial state across single-axis conditions and a matched simultaneous condition. This design reveals two opposing outcome changes that aggregate success rates cannot distinguish: emergent failures, where all single-axis rollouts succeed but the simultaneous rollout fails, and compensated successes, where at least one single-axis rollout fails but the simultaneous rollout succeeds. Because one transition decreases compound success while the other increases it, they can cancel, making aggregate compound performance appear consistent with single-axis measurements even when individual outcomes differ substantially. These opposing transitions can largely cancel in aggregate: even when the difference between the two transition rates is not statistically distinguishable from zero, as many as 29.0% of matched initial states still change outcome. Across six policies and three severity levels, such outcome changes reach 34.5% in the most affected condition. The relative prevalence of the two transitions varies across policies and severities, while the transition rates remain similar under independent re-evaluation of stochastic policies. Compound robustness therefore cannot be characterized from aggregate single-axis success rates alone; matched per-instance evaluation is needed to reveal how joint perturbations alter behavior.

Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with evolutionary search through critique, comparison, and revision. However, how different forms of agent collaboration affect hypothesis quality remains an open question. Answering this question requires separating the effects of agents' scientific capabilities from those of their collaboration. A framework must therefore preserve agents' scientific roles and support rules for combining, revising, and retaining hypotheses. Building on this view, we introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population. Specifically, we propose a generational genetic algorithm to coordinate specialized large language model (LLM) agents that integrate mechanistic arguments, reconsider assumptions, and assess evidence and testability. Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable. Moreover, we design our evaluation around scientifically meaningful hypotheses that explain how a proposed intervention could work. Drug repurposing links these explanations to target-level biological claims assessed against external evidence. Specifically, we adapt DepMap and Open Targets into complementary external measures grounded in experimental, genetic, and clinical evidence. Across 34 cancer types, HypoEvolve achieves the highest scores against six baselines on both measures. DepMap selectivity reaches 0.171, versus 0.115 for the strongest baseline. Gains over single-pass generation also generalize to held-out cancer types. HypoEvolve advances a vision of autonomous science in which AI research teams achieve a capacity for discovery beyond that of individual models.

Dexterous manipulation of deformable objects demands continuous fingertip-level regulation of pressure, friction, and incipient slip. We study one of the most challenging cases: dexterous cable tracing, feeding a cable through the hand with repeated pinch-and-curl motions of the thumb and index finger. We introduce Touch2Trace, a tactile-driven imitation-learning system for this task, and provide, to our knowledge, the first systematic real-world characterization of how encoder pretraining, control rate, temporal context, and spatial resolution each shape policy performance. The winning learning recipe combines a tactile encoder pretrained for a custom 32 x 32 piezoresistive sensor (TacV5) via self-supervised learning with a lightweight transformer policy trained on teleoperated demonstrations via behavior cloning, deployed at 60 Hz on a Tesollo DG-5F hand. Tactile feedback without vision or explicit cable-state estimation significantly improves tracing performance versus a proprioception-only baseline: from 0.2 cm to 20.1 cm mean distance and 0% to 93% success rate, with zero-shot transfer to unseen cables and routing conditions. The results quantify the influence of key parameters in tactile-driven systems for reliable dexterous deformable object manipulation.

Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL in real-world tasks is hindered by safety requirements, which have been underexplored in prior work. In this paper, we propose a safe meta-RL framework that explicitly accounts for safety during adaptation. Our key insight is to reason about safety in the information space, which captures both the physical state and the agent's belief over the underlying task. Within this space, we introduce a safety value function that measures the probability of the agent avoiding unsafe regions indefinitely. We show that this function satisfies a self-consistency condition and a Bellman equation, which make it learnable via meta-RL. Based on this formulation, we develop a safe meta-RL algorithm that learns the safety value function and leverages it for safety filtering and constrained policy optimization. Experiments on meta-RL benchmarks demonstrate the effectiveness of the proposed method.

Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework built on TacV5, a compact sensor integrating a $32 \times 32$ piezoresistive array operating at 240 Hz and a 3-axis MEMS accelerometer operating at 8 kHz. The piezoresistive array captures spatial pressure distributions, while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. Experiments on a dataset of 1.4 million frames spanning 37 objects demonstrate the complementarity of the two modalities. SlipSense achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. When trained solely on UMI data, SlipSense generalizes zero-shot to a Tesollo dexterous hand, transferring across unseen objects, distinct sensor units, and robotic platforms without retraining.

Physical AI relies on frequently-updated, latency-sensitive video stream to perceive, reason, and interact with the physical world, resulting in strict latency requirements with much higher data volumes that existing 5G networks cannot support. Goal-oriented communication (GoC) offers as a promising approach to solve this challenge by transmitting only task-relevant semantic representations. However, existing GoC frameworks were mainly evaluated in the simulations while their effectiveness has never been validated in a practical deployment of physical AI application. In this work, we develop an end-to-end GoC testbed for Physical AI, which connects a PiPER robot arm equipped with an RGB-D camera and a 5G modem to an NVIDIA Jetson AGX Orin edge server through a 5G OpenAirInterface network. We propose and implement three GoC frameworks that transmit 3D bounding boxes, 2D scene graphs, and 3D scene graphs, as three types of semantic representations, respectively. They share the common functional modules designed for closed-loop Physical AI applications, including semantic extraction, full stack 5G transmission, language model inference, digital twin validation, and robotic control. Extensive experiments on our testbed show that our GoC frameworks reduce the task completion time by up to 52.6% and improve task success probability by up to 45%, compared to the traditional framework that periodically transmits the raw image data. These results validate the practical effectiveness of our GoC framework and pave the way for efficient and reliable Physical AI applications over future 6G networks. Project website: https://sites.google.com/view/goc-physical-ai-testbed.

Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier training stage, can shape which of these properties later generalise. We introduce Inoculation Midtraining, a technique that teaches a base model that unsafe behaviour belongs to a designated <quarantine_token> context, as indicated by the <quarantine_token> neologism (a new token) introduced during midtraining, and then post-trains the model on unsafe data within that context. We then evaluate the model outside the context, with the <quarantine_token> neologism excluded from the system prompt. Across supervised fine-tuning and reinforcement learning post-training regimes, we find that Inoculation Midtraining can reduce misalignment while preserving the transfer of benign data properties (e.g., speaking in German or Shakespearean prose). However, our approach does not outperform standard Inoculation Prompting, is sensitive to training configuration, and produces a leaky boundary that nearby contextual cues can reactivate. These results show that inoculation with a learned association introduced via midtraining can shape selective generalisation. Still, more work is needed before this approach can become a load-bearing component in a developer's safety framework.

Uncrewed Aerial Manipulators (UAMs) extend the capabilities of Uncrewed Aerial Vehicles (UAVs) from perception to physical interaction. Among various aerial interactions, push-and-pull operations are fundamental manipulation primitives that require sustained horizontal forces while maintaining stable flight. In this paper, we propose DuctAM, a compact aerial manipulation platform that enhances horizontal force capability for push-and-pull interactions using two ducted fans integrated along the quadrotor interaction axis. An attitude-force decoupled control scheme enables controllable horizontal forces without requiring large attitude changes. Extensive real-world experiments are conducted to validate the DuctAM. Figure-eight trajectory tracking experiments demonstrate stable flight and accurate motion control in both quad and duct modes. Force-measurement experiments quantify the decoupled longitudinal force capability of DuctAM. Finally, representative push-and-pull interaction tasks, including cart pushing, door closing, and drawer opening, verify the practical effectiveness of DuctAM. The results show that DuctAM achieves significantly improved horizontal interaction force capability while maintaining stable flight compared with conventional UAVs.

People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised. We developed K-Bench, a clinician-calibrated, protected benchmark evaluating 125 model configurations representing 33 base models from 14 providers across a fixed cohort of 200 multi-turn vignettes involving suicide, self-harm, domestic violence, substance misuse, and no-risk presentations. Synthetic patient conversations showed substantial distributional overlap with real human-AI conversations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible item comparisons from 151 clinician-rated transcripts. Leading models combined strong supportive conversation with combined-risk scores above 95, whereas risk exploration exposed substantial variation among lower-performing configurations. Therapeutic prompting produced configuration-specific gains concentrated among weaker models, while elevated reasoning produced no average improvement. K-Bench combines broader clinical coverage and configuration-scale comparison with a continuously updated public leaderboard whose operational test materials are protected from direct optimisation. The leaderboard is available at www.k-bench.ai.

Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we propose Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory. The actor remains frozen, while the LLM-as-a-Coach is trained to maximize a reward given by the correctness of the actor's guided response. We study two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance reward, which elicits knowledge that transfers to other instances. Across mathematical reasoning and interactive text-games, L2C consistently outperforms self-refinement and an untrained LLM-as-a-Coach. Running experiential learning for more iterations further improves accuracy and uses additional inference compute more effectively than enlarging the actor's decoding budget. The trained LLM-as-a-Coach also transfers to out-of-distribution tasks and adapts its guidance to the specific actor it coaches.

Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM personas simulate public opinion at scale. Current evaluations test only whether personas hold the right opinions -- a static snapshot. But opinion research increasingly depends on dynamic fidelity: whether personas update beliefs in response to new arguments, as humans do during deliberation. No existing benchmark tests this. We introduce the Deliberative Polling Diagnostic Framework, which compares human and LLM belief shifts after identical informational interventions. Grounded in deliberative polling, it surfaces failures invisible to static evaluation: models that produce plausible partisan opinions can still misrepresent how those opinions change. Applying the framework to five frontier models using data from America in One Room (526 personas, 72 questions), we find that every model fails, each in a unique manner. GPT-5.1 exhibits reversal: its personas become more hostile toward the opposing party after balanced information, while humans become less so. This reversal is selective (80% on outgroup vs. 26% on policy questions) and symmetric across partisan identities. Gemini 2.0 Flash, Claude Sonnet 4.5, and Llama 3.3 70B exhibit overshoot, shifting correctly but at 5-7x human magnitude. DeepSeek V3 exhibits rigidity with near-zero change. Targeted ablations reveal that policy content triggers these failures and that they are identity-specific: GPT-5.1 reverses on outgroup questions but overshoots on ingroup; Gemini shows the inverse. We term this signature self-sycophancy: conformity to the model's internal stereotype of the persona rather than reasoning from the information provided. Our framework offers a concrete protocol: run the deliberative diagnostic before trusting LLM personas to mimic revised beliefs.

Learning chunk-based visuomotor policies for long-horizon robot manipulation remains challenging. Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences. However, their failures are often dominated by prediction errors at a small number of critical timesteps rather than uniformly poor predictions across the entire action chunk, making uniform refinement inefficient and insufficiently targeted. To address this bottleneck, we propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies. Specifically, UGR follows a coarse-to-refine design: it first predicts a full action chunk, estimates per-step temporal uncertainty from the coarse hidden states, and applies residual correction only to the most uncertain timesteps selected by a binary mask. The uncertainty branch is decoupled from the coarse action predictor, enabling clean attribution of the refinement gains to uncertainty-guided correction rather than additional predictor capacity. Extensive experiments on five dual-arm manipulation tasks from the RoboTwin benchmark show that UGR achieves the best success rate on four tasks, improves over the ACT baseline by up to 13% absolute, and outperforms both full-chunk and position-agnostic block refinement in ablation studies.

Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are grounded, citation-valid, or appropriately refused. This paper introduces CiteGuard-RAG, a validation-centered AI system for evidence-grounded question answering. The system integrates hybrid semantic-lexical retrieval, citation-constrained generation, sentence-level grounding validation, and single-pass regeneration. Validation is used at runtime to determine whether a candidate answer should be accepted, refused, or regenerated before final delivery. CiteGuard-RAG is evaluated on 400 questions across a controlled housing-law dataset, PrivacyQA, and CUAD. In the controlled evaluation, it achieves 99.1% retrieval accuracy, 98.3% grounded-answer accuracy, and 98.3% citation validity, with no validation-detected hallucinations. Ablation results show that grounded-answer accuracy drops sharply when validation is removed, even when retrieval accuracy remains unchanged. External evaluation shows that while citation validity remains strong, evidence utilization, span alignment, and refusal calibration become harder under domain shift. These findings indicate that trustworthy RAG systems require explicit validation between retrieval and final answer delivery. CiteGuard-RAG provides a practical architecture for linking retrieval, generation, citation checking, abstention, and regeneration in high-stakes information access.

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behaviors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code: https://github.com/ruc-datalab/EvoOntology

Light detection and ranging (LiDAR) remains less explored than RGB-D sensing for perceptive legged locomotion, and existing LiDAR-based approaches often rely on explicit mapping. We present JEPLO (Joint-Embedding Predictive learning for legged LOcomotion), a single-stage learning framework for mapping-free, LiDAR-based perceptive locomotion for legged robots. We introduce a proprio-exteroceptive JEPA (PE-JEPA) world model to learn predictive egocentric terrain representations from onboard observations, including raw LiDAR scans. A concurrent JEPA-teacher-student (CJTS) pipeline is further proposed to train a locomotion policy informed by JEPA latent representations in simulation using deep reinforcement learning with a simple reward formulation. The framework achieves successful sim-to-real transfer, enabling omnidirectional traversal of diverse terrains, including long staircases and high boxes, with lightweight onboard computation. Evaluations demonstrate greater robustness than existing perceptive locomotion frameworks, particularly under degraded perception caused by occlusion, sparsity and noise. Further analysis validates JEPLO's ability to retain task-relevant information under these challenging conditions. We open-source our implementation, experimental datasets, and hardware setup designs https://github.com/ASIG-X/JEPLO.

Full-duplex speech-to-speech (S2S) models enable natural conversational AI by allowing simultaneous listening and speaking. However, these models typically lack inherent user speech transcription, which is essential for applications such as conversation logging, accessibility features, and quality monitoring. In this work, we propose an efficient method to add streaming ASR capabilities to an existing duplex S2S model by introducing a lightweight ASR head in parallel to the agent text head. Our approach requires minimal additional parameters and no significant architectural changes to the base S2S model, enabling real-time user transcription while preserving full-duplex conversational capabilities including turn-taking and barge-in handling. Experimental results demonstrate that our method achieves streaming average WER of 10.21% on the HuggingFace Open ASR Leaderboard within the duplex S2S framework. Additionally, we show that the same architecture trained as a standalone streaming ASR model achieves competitive results (7.73% WER) compared to current SOTA models. We will open-source our training and inference code to facilitate further research in joint streaming ASR and S2S modeling.

This paper studies the strategic market participation of a monopolistic energy storage aggregator (ESA) in a day-ahead electricity market. The ESA coordinates geographically distributed storage units, submits a coordinated bid for its portfolio, and may hold financial transmission rights (FTRs). The system operator clears the market through a network-constrained, multi-period economic dispatch, determining generation and load schedules, nodal prices, energy-market payments, and FTR payoffs. We formulate the ESA--system-operator interaction as a Stackelberg game and characterize its equilibrium through a constraint-binding-pattern decomposition of the market-clearing problem. Beyond enabling equilibrium computation, the framework reveals how the ESA can increase its profit by strategically inducing or avoiding particular constraint-binding patterns. It also establishes a novel welfare result: although strategic storage without FTRs is known to weakly improve social welfare relative to the no-storage case, certain FTR positions can overturn this guarantee by strengthening the ESA's incentive to induce particular patterns, causing social welfare to fall below the no-storage level. Motivated by these findings, we develop two system-operator mechanisms for limiting undesirable ESA behavior and its adverse effects on market outcomes and social welfare. Finally, a three-bus study illustrates the theoretical findings, while IEEE test systems demonstrate the scalability of the proposed method.

Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neither post-hoc correction nor weight-level intervention can effectively preempt. We propose DescaPE (DEcoding Signal Control Against Path Error-snowballing), a decoding framework that leverages internal model signals to suppress hallucination-prone trajectories at inference time. Through sliding-window MLP ablation, we identify a factual-salient layer span within LLMs whose derived signal is selectively elevated for factual tokens and exhibits anomalous spikes at hallucination-prone steps. We train a lightweight probe to approximate this signal from a single forward pass and integrate it into candidate scoring to penalize high-risk continuations while rewarding factually grounded ones. Experiments across five factuality benchmarks on three LLMs demonstrate that DescaPE achieves factuality improvements over decoding-time baselines in multiple settings, while incurring only 1.10x latency overhead in our efficiency evaluation. Our code is available at https://github.com/hayeonggg/DESCAPE.

Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods such as shallow fusion and density ratio are well-established methods that incorporate external LMs during ASR decoding. However, they incur additional computational costs due to LM inference, which is particularly problematic for recent larger LMs. In this study, we propose incorporating external LMs via model merging. This method integrates the LMs directly into the parameters of an LLM-based ASR model, requiring no additional computational cost at inference. We formulate domain extension and transfer via arithmetic operations on LoRA parameters. Experimental evaluations were conducted for the domain adaptation of LLM-based ASR trained on CSJ and LibriSpeech. We show that our LM merging consistently improved the ASR performance in the target domains, without degrading inference speed or memory footprint.

Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not converged to a common design. Dexterous hands differ in finger structure, contact surfaces, and sensor layouts, while simulated tactile signals still differ from measurements produced by physical sensors. These factors make it difficult to study visuo-tactile manipulation across diverse dexterous hands within a consistent experimental setting. We present Bench2Dex, a simulation benchmark for visuo-tactile bimanual manipulation across 12 dexterous hands. We adapt existing robot models with a shared simulated tactile interface that converts local contact geometry into image-like tactile observations. The interface provides a consistent observation format across different hand morphologies without attempting to reproduce the output of a specific physical tactile sensor. Bench2Dex includes 26 bimanual manipulation tasks that involve tool use, articulated-object interaction, and multi-stage manipulation, together with about 1.3K human-teleoperated demonstrations. The benchmark provides synchronized visual, tactile, proprioceptive, action, and object-state observations, together with executable task metrics. For robustness, we group seven perturbation types into invariance axis, where the correct action does not change, and equivariance axis, where the correct action changes together with the perturbation. We evaluate ACT, Diffusion Policy, pi0.5, and GR00T N1.5 on Bench2Dex and report their performance and failure modes. Bench2Dex is meant as a platform for studying visuo-tactile learning across dexterous hands. It does not assume that simulated tactile observations can replace real tactile sensing; it offers a shared setting for algorithm development while tactile hardware and simulation models are still evolving.

Learning Model Predictive Control (LMPC) improves iterative control tasks by using previous executions to construct the terminal constraint and terminal cost of the MPC problem. Although effective, this reuse of past trajectories can make LMPC sensitive to the initial data. In particular, LMPC may repeatedly exploit stored trajectories with favorable cost-to-go values while insufficiently exploring alternative route patterns that could yield lower cost after further improvement. To address this issue, we propose Multi-Modal LMPC (MM-LMPC). The proposed framework clusters past trajectories into motion modes, constructs a mode-specific LMPC controller for each mode, and uses an LCB-based meta-controller to select which mode-specific controller to execute at each iteration. Mode information is incorporated into the terminal constraint and terminal cost through two designs. The hard-constrained design uses mode-specific terminal constraints and terminal costs constructed from the data associated with each mode. The soft-regularized design retains a shared terminal constraint while adding membership-based penalties to the terminal cost. These designs reduce the bias caused by pooling all trajectories into a single terminal memory while retaining the recursive feasibility and stability structure of LMPC. Our theoretical analysis shows that both designs preserve recursive feasibility and closed-loop stability. For the hard-constrained design, we further establish mode-wise cost convergence, asymptotic best-mode performance, and a logarithmic cumulative regret bound under the LCB rule. Simulations on multi-route obstacle-avoidance tasks show that MM-LMPC improves exploration and achieves lower costs than standard LMPC.

Planning in complex environments requires task specifications grounded in representations that capture objects, relations, and affordances; scene graphs meet this need, but their size in large environments hinders efficient planning. While task-aware pruning and hierarchical abstractions have been explored, a general, task-centric formalization of what constitutes a sufficient scene graph for planning remains open. This paper provides such a formalization by modeling planning over scene graphs within an information-spaces framework through the definition of scene graph transition systems and relevant action semantics for navigation and manipulation. We then introduce derived scene graphs via information mappings that merge and prune nodes and induce quotient transition systems augmented with motion primitives to capture higher-level actions over merged graph nodes. Sufficiency is characterized by two conditions: (i) the information mapping yields a deterministic quotient, and (ii) the task is well-posed over derived traces, ensuring plans found on the derived model are feasible on the maximal system. We illustrate the framework using a task over an example environment, showing both sufficient and insufficient reduced scene graphs.

World Action Models (WAMs) use video generation models to predict future visual dynamics for robotic manipulation, but iterative denoising introduces additional latency for closed-loop control. We empirically find that visual content converges at different rates during denoising. Static background structure forms early, whereas the gripper and manipulated object remain blurry after the first step, with their interaction dynamics emerging only through subsequent denoising. Consequently, naively truncating a multi-step video model to one step preserves scene structure but loses the interaction-centric dynamics most critical for manipulation. To address this issue, we propose DIDO, which distills the converged dynamics of a multi-step video model into a single denoising step. DIDO combines distribution matching distillation with interaction-centric representation guidance. Beyond compressing multi-step generation into one forward pass, DIDO explicitly models the gripper, manipulated object, and their interaction using supervised bounding-box visual reasoning tokens. Additionally, DIDO aligns the target object's representations across multiple model layers with features from a pretrained DINOv3 encoder. This interaction-centric guidance helps the distilled model preserve both the relevant entities and their future dynamics in a single step, while substantially reducing inference latency. DIDO achieves an average success rate of 99.0\% on LIBERO, 76.6\% on LIBERO-Plus, and 92.0\% on RoboTwin, while also demonstrating effective transfer to long-horizon and generalization tasks in real-world robotic manipulation.

Recent advances in robot imitation learning have produced visuomotor policies that predict actions directly from visual observations. Yet visually similar scenes can require different actions as target position, object height, or contact geometry changes. Pretrained RGB features may map these geometrically distinct states to similar policy inputs, while simply adding depth requires the policy to learn RGB-depth correspondence from the same limited demonstrations used to learn control. We introduce StereoPatch, a patch-aligned RGB-depth representation that binds registered metric geometry directly to the RGB patches used for action prediction. On a shared 2-D patch grid, asymmetric cross-attention incorporates depth information into the corresponding RGB features before action decoding. The resulting StereoPatch Tokens provide a geometry-aware visual representation that can condition general visuomotor policies without changing their underlying learning objectives. Across six real-robot tasks, StereoPatch achieves higher closed-loop success than appearance-only, geometry-only, raw RGB-D, and late-fusion baselines. Additional experiments across three simulation suites evaluate compatibility across visuomotor policy architectures, spatial generalization, and operating limits. Results suggest that resolving control-relevant geometric ambiguity benefits from aligning depth directly with the visual features used for action prediction, rather than supplying it as an independent modality. Project page: https://aus.bot/research/stereopatch/.

Optimizing the sensitivity of the unbalance voltage in Wheatstone bridges with respect to bridge parameter changes remains a fundamental objective in circuit design and instrumentation. When accounting for finite source and detector resistances, determining the optimal bridge configuration becomes increasingly complex, and a analytical representation of the optimal solution has not yet been established. This paper derives a novel analytical representation of the optimal configuration for finite source and detector resistances. Furthermore, the proposed optimal solution is benchmarked against the conventional equal-arm configuration.

A robot following language instructions needs its semantic memory to keep naming the same physical object while the SLAM pose graph underneath is optimized, loop-closed and compressed. Maps committing each detection to a world coordinate cannot: a closure moves the anchor it was measured from, or the solver marginalizes that anchor, and the query then selects a different object although both graphs represent the same posterior. P-POSEMEM stores each observation as an immutable event at its birth keyframe, retains the Bayes-tree elimination conditional of every marginalized keyframe, and integrates the semantic likelihood over the reconstructed joint posterior of poses, anchors and identities. Dproj, the total-variation defect between the language-goal distributions of inference-equivalent full and marginalized graphs, measures this directly. Over 40 HM3DSem scenes and 112,000 queries, P-POSEMEM reproduces the full-graph oracle (Dproj = 0) and reduces goal flips against every memory-reducing baseline. On an eight-run campaign whose 761 closures rewrote the map by up to 47 m, Dproj stays below 10^-13 with 0/288 goal flips when elimination follows the closures, where every ablation and a coordinate committed at insertion flip goals it does not; under a live bounded solver the same memory flips 23/288 against 53 for that frozen coordinate. A pre-registered negative control is detected by Dproj while leaving calibration error and navigation success unchanged, indicating that these measures capture distinct failure modes. Retrieval is held fixed by a shared frozen detector, isolating the gain to memory consistency. Code and data: https://anonymous.4open.science/r/posemem-2328/.

Companion robots face everyday situations in which several feasible behaviors may be appropriate, yet different people prefer different responses. We introduce InterSocialBench, a benchmark of 210 domestic scenarios and 18 high-level behaviors, pairing judgments from 100 human participants with 23,520 responses from seven large language models under 16 personality conditions. Each human annotation preserves a preferred action alongside explicitly appropriate and inappropriate candidates. A structured construction pipeline covers behavioral alternatives, competing situational cues, and relevant history and future tasks. Evaluation distinguishes preferred-choice agreement from explicit rejection, using scenario-grouped splits for trainable predictors. Simple frequency and persona-voting baselines illustrate these objectives. Across the tested prompts, model and human behavior distributions differ, and the diversity gap remains after matching response counts: humans exhibit 4.68 distinct choices per scenario, compared with 2.06--3.46 for the models. Human scenario-level plurality agreement is 51.5%, describing disagreement rather than a universal prediction ceiling. InterSocialBench supports evaluating social behavior selection without replacing individual judgments with a single consensus label.

Structured spatial data require quantum encodings that preserve geometric relations, expose measurable observables, and remain implementable on finite-depth hardware. This work introduces a quantum representation and circuit architecture for rigid-body transformations and specializes it to Denavit--Hartenberg kinematics of serial open-chain manipulators. Each translational contribution is factorized into a classical metric magnitude and a signed unit direction encoded by a single-qubit Bloch vector, while parameterized rotations reproduce the ordered propagation of frame directions. A selector register prepares probabilities proportional to the contribution magnitudes, and the reduced state of a designated readout qubit encodes their normalized weighted sum. The retained classical scale then reconstructs the metric end-effector position. Two additional readout qubits encode terminal-frame axes, providing a compact and geometrically interpretable pose interface. At the ideal expectation-value level, measured Pauli observables reproduce the corresponding classical kinematic quantities. Alternative circuit architectures realize the same representation with different tradeoffs in qubit count, circuit depth, controlled operations, and measurement requirements. Validation on a serial manipulator yields numerically negligible position and orientation reconstruction errors under ideal simulation. Finite-shot simulations, noisy executions, transpilation analysis, and a hardware demonstration further characterize statistical error, noise sensitivity, and implementation overhead without asserting computational advantage.

Expanding integrated photonics into the blue spectral range requires high-performance light sources, making the gallium nitride (GaN) material family indispensable. While silicon nitride (SiN) platforms offer a robust, CMOS compatible passive ecosystem for visible wavelengths, seamlessly integrating GaN lasers remains a major bottleneck. Conventional heterogeneous integration methods present distinct trade-offs: full-wafer bonding achieves high throughput but requires careful management of thermal and lattice mismatches across large areas, whereas flip-chip bonding ensures high yield through pretesting but is constrained by sequential processing speed. In this landscape, micro-transfer printing (MTP) emerges as a disruptive, material-efficient alternative, bypassing these limitations by combining high-density parallel integration with known-good-die selection. Applying MTP to GaN, however, presents a significant material challenge: due to its chemical inertness and strong III-N bonds, device release typically relies on electrochemical etching, which can compromise material quality. Here, we overcome this hurdle and demonstrate the first micro-transfer printed blue lasers on a SiN platform. Using a heavily doped n-type sacrificial layer together with optimized electrochemical etching conditions, we release smooth-surfaced thin-film light sources from bulk GaN substrates. Following release, the devices are integrated and butt-coupled to SiN fork-shaped edge couplers, achieving high current densities exceeding 20 kA$/$cm$^2$ alongside lasing at 455 nm. These results expand the visible integrated photonic toolkit and establish a framework for multi-wavelength integration, opening new avenues for next-generation technologies including flow cytometry, quantum computing, optical communications, and augmented/virtual reality.

Wheel-loader excavation is a sequential decision problem in which every scoop changes the terrain available to subsequent actions. A practical world model must predict action consequences accurately, rank candidates in real time, and operate inside the closed loop of a full-size machine. We present the World-Action Model (WAM), which proposes multiple scoops, rejects geometrically inadmissible candidates, jointly predicts signed terrain change and loaded volume, executes the candidate with the largest predicted load, and replans from the newly observed terrain. On 32 geometry-disjoint MinSlope test episodes, adding world-model ranking to matched diffusion proposals reduces the mean scoop count from 651.8 to 540.6 (17.1%), preserves 32/32 completion, and improves every paired episode. In a complete-system comparison, WAM completes 32/32 episodes versus 29/32 for an independently trained soft actor-critic policy. Comparisons of input representations, spatial support, and five architectures identify an accurate and efficient physics-structured predictor. We further evaluate the interface on event-disjoint full-size-loader data and deploy the complete perception-proposal-prediction-selection-execution loop for autonomous excavation. The ROS2/TensorRT implementation processes five candidates in 72.4 ms on a Jetson AGX Orin. The simulation results establish decision-level gains, while the physical experiments demonstrate real-world closed-loop feasibility.

This letter investigates how the parameters of a slope-aware variable-admittance filter influence user preferences in force-based interaction with a robotic guide dog for visually impaired individuals. The proposed system consists of a quadruped robot equipped with a sensor-free rigid handle for physical guidance. The framework combines path following, momentum-based interaction-wrench estimation, and a variable-admittance filter whose stiffness and damping are adapted online from slope information extracted by the robot's depth camera. The adaptation policies are evaluated through high-fidelity simulations and a human-subject study involving blindfolded sighted participants. Multiple strategies are compared using a Taguchi L9 design of experiments. Preliminary main-effect results suggest that increasing stiffness uphill and decreasing it downhill improves both objective and subjective metrics, whereas damping shows no significant main effect.

Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.

We introduce the Universe of Universes (UoU) framework, which treats the full ecosystem of major large language models (LLMs) as a structured retrieval corpus and proposes a compositional Automated Reasoning (AR) and Machine Learning (ML) architecture for cross-model retrieval-augmented generation. The central contribution is the formal characterization of the Benefit Yield Function (BYF), the marginal performance gain per additional model added to an ensemble, and the identification of the implosion threshold θ*: the ensemble size at which BYF crosses zero and aggregate performance begins to degrade. Existing LLM ensemble and mixture-of-agents systems treat models as responders and aggregate outputs, but do not study performance as a function of ensemble size N across the full model universe. Benchmark research confirms performance plateaus at the individual model level; model collapse literature establishes that iterative training on AI-generated outputs degrades individual model distributions. Neither body of work formalizes the ensemble-level implosion threshold, models Epistemic Hereditary Drift (EHD) at the ecosystem level, or treats AI manufacturing velocity as a co-variable of θ*. The framework has direct implications for DoD multi-model AI acquisition policy and the emerging science of testing AI-enabled systems.

Lithium niobate on insulator (LNOI) combines the outstanding optical properties of lithium niobate (LN) with strong optical confinement, scalable fabrication and high-density integration, making it a leading platform for integrated photonic chips. Recent advances in LNOI photonics have mainly centred on passive and electro-optic components, including couplers, waveguides, microcavities and modulators, whereas efficient on-chip laser sources remain insufficiently developed, limiting the realization of fully integrated LN photonic systems. Because LN is an indirect-bandgap material, lasing on LNOI generally relies on photoluminescence from rare-earth-ion doping, yet the conversion efficiency of doped LNOI lasers has remained low. By comparing LNOI microcavity lasers with fibre lasers and waveguide amplifiers, we identify the limited number of rare-earth ions participating in stimulated emission as a key factor responsible for inefficient pump utilization. Here we demonstrate an integrated Er-doped LNOI laser that combines high-quality, highly Er-doped LN, a large-diameter wide-microring resonator, a low-loss waveguide amplifier and bidirectional pumping. This architecture enables a slope efficiency of 16.91% at 1562 nm, exceeding 10% on the LNOI platform for the first time. Our results provide a route towards high-efficiency LNOI lasers for fully integrated photonic systems.

This paper presents a low-clearance hinge joint mechanism based on the 3D printing on sheet fabrication method. This approach simplifies the fabrication of hinge mechanisms and overcomes limitations of conventional origami manufacturing by eliminating the need for adhesives commonly used during assembly, making it suitable for robots at the tens-of-centimeters scale. The advantages and disadvantages of three types of hinge joint mechanisms are compared, and a hinge joint that can be designed with low clearance for various facet thicknesses is selected. Based on the selected hinge joint, the twisting angle and bending force are analyzed, leading to the implementation of a clearance of 0.1 mm. Torsional resistance is experimentally evaluated to measure the torque required for twisting caused by plastic deformation and clearance. The results show that the torque associated with plastic deformation is sufficient to constrain the undesired degrees of freedom of the hinge joint, while the torque required for twisting due to clearance is minimal. Based on the analyzed data, the proposed hinge joint mechanism is applied to a 3-degree-of-freedom delta robot manipulator, demonstrating precise motion with low clearance.

Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even when the end-user task is non-English. We fill this gap by evaluating a two-agent extraction-answer core, with an additional back-translation agent in the English-forced condition, across four typologically diverse languages (Hindi, Chinese, Spanish, Arabic; n = 300 per language) using the Aya-23-8B model. We compare a native-language pipeline to an English-forced one (which incorporates a final back-translation step from English to the user's language). We discover a statistically significant English-Forcing Tax (surviving a strict Bonferroni correction) that isolates the cost of English routing from general multi-agent orchestration overhead. Forcing inter-agent communication through English reduces Exact Match accuracy by 13.0 percentage points (Spanish) up to 30.6 percentage points (Hindi) compared to native-language multi-agent execution. Using chrF scores as a diagnostic measure of English-reference lexical overlap, we find that lower overlap is strongly associated with pipeline failure, consistent with translation loss being an important contributor to the observed performance drop. These findings suggest a compelling case for native-language routing in agent frameworks when the source and target languages are typologically distant, reducing a compounding translation tax.

Multi-robot Control Barrier Function (CBF) safety filters can become infeasible, but a failed quadratic program (QP) does not indicate why the conflict occurred or how to resolve it. To address this, we develop an exact feasibility certificate for multi-agent CBF filters with heterogeneous control-affine dynamics and convex input sets. The certificate quantifies a feasibility reserve by separating the demand imposed by safety constraints from the available actuator supply. This decomposition shows when CBF gain tuning or increased actuation can and cannot resolve infeasibility, and identifies the agents and interactions responsible for the conflict. We further propose an algorithm to optimally allocate shared safety constraints by maximizing the worst local feasibility margin, yielding a linear program for polyhedral input sets. In $320$ paired closed-loop simulations, the proposed allocation reduces infeasible control steps from roughly $50\%$ to $6.2\%$, and reduces safety-violating runs from $118/160$ to $24/160$. In addition, across $52$ infeasibility events, the certificate identifies an interaction whose relaxation restores feasibility in $94\%$ of cases.

Data-driven materials development requires the collection of large amounts of high-quality materials data. Full autonomy of materials experiments is anticipated, but its technical hurdles are high and its adoption remains limited. In this study, we constructed a simple, easy-to-deploy automated experimentation platform that focuses not on full autonomy but on the reliable automation and quantitative recording of experimental processes. Specifically, commercially available instruments such as robot arms, electric pipettes, web cameras, and an electronic balance are combined, components such as fixtures are fabricated with a 3D printer, and the instruments are operated by control code generated by an AI agent based on a large language model. As a demonstration, we applied the platform to a two-solution mixing experimental system and synthesized ZIF-8, a metal-organic framework. A white suspension phase was observed in the product, and X-ray diffraction measurements confirmed that it was ZIF-8. We also found that its particle size distribution depends strongly on the solution dispensing speed of the electric pipette, which is a parameter that is difficult to control or record in manual operation. This dependence was reproduced in repeated runs, confirming the repeatability of the automated synthesis. This result is a good example showing that the control and recording of process parameters that are rarely quantified in manual work can govern the quality of materials data. All control code, CAD models, and documentation are made publicly available to encourage the spread of laboratory-scale automation of experiments.

A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at inference time. This degradation is especially limiting for applications requiring open-ended exploration and pluralistic perspectives, such as scientific ideation and creative writing. We present MoDA (Mode-conditioned Diversity Alignment), an online post-training RL algorithm that jointly optimizes generation quality and diversity, inspired by the coordination perspective in multi-agent reinforcement learning (MARL). MoDA trains a single shared LLM policy conditioned on abstract numbered roles, where each role acts as an agent competing to produce outputs distinct from the others. This formulation encourages mode-conditioned agents to explore complementary regions of the high-quality output space without requiring hand-crafted personas or architectural modifications. MoDA employs a prompt-adaptive quality gating mechanism that calibrates a reference quality threshold and grants diversity rewards only to responses that meet the threshold, preventing reward-hacking behaviors that compromise response quality. To study quality-diversity tradeoffs, we evaluate MoDA on a comprehensive suite of benchmarks spanning seven general capability tasks and four domain-specific diversity tasks in scientific ideation and creative writing. MoDA improves SBERT diversity by 265% on the Infinite-Chat held-out prompts, while increasing average general capability pass@1 by 10.3% over the Qwen3-8B baseline. Compared with the strongest DivPO baseline, MoDA improves SBERT diversity from 0.274 to 0.482 (+75.9%) and E-Vendi from 2.86 to 4.4 (+53.8%), while improving average general capability pass@1 by 7.0%. Overall, MoDA provides a drop-in alternative to standard post-training methods that preserves and expands the model's expressive output space while improving quality.

Ptychography overcomes the limits of lenses by co-designing optics and computation. Yet prevailing implementations reconstruct on a pixel grid, where weakly-constrained modes drift and recovery demands redundant data. Here we introduce Gaussian-splatting ptychography, representing object and probe as Gaussian primitives. Relocation concentrates primitives where structure is dense, and overlapping primitives couple neighbouring pixels to suppress mode drift. The scheme unexpectedly restores the low-frequency phase that conventional approaches lose, enabling uniform phase transfer across spatial frequencies. The probe is represented and updated in its pupil plane from a random start. In Fourier ptychography, the pupil-plane model recovers severe aberrations where pixel-grid solvers fail. In conventional optical, X-ray and electron ptychography, the pupil-plane primitives also recover the real-space probes with no model of beam-forming optics. The representation cuts memory up to 14-fold and recovers specimens from fewer acquisitions. At electron wavelengths, it resolves atomic structure at tens of electrons per square angstrom.

As conversational AI systems increasingly operate in sensitive domains, the central challenge shifts from usability to trust calibration, ensuring that users rely on systems neither too much nor too little. Systems that provide advice or interpretations risk encouraging inappropriate reliance, particularly when users perceive AI outputs as authoritative. We present CASELy, a conversational agent explicitly designed to limit its own authority through non-advisory Socratic dialogue. The agent asks reflective questions grounded exclusively in user input and refuses to provide advice, recommendations, or interpretations. This design operationalizes trust calibration by constraining agent agency rather than optimizing capability. In a pilot randomized controlled study with higher education students, participants interacting with the Socratic dialogue reported substantially higher user experience (UEQ-S overall = 1.50) compared to a non-dialogue control (0). Qualitative findings identify three mechanisms supporting calibrated trust: transparency through visible grounding, preservation of user decision authority, and reduced fear of judgment. We argue that appropriate reliance can be achieved through interactional constraints, offering a design pattern for trustworthy conversational AI in sensitive contexts.

Tunable low-noise lasers are crucial components employed in modern metrology. Advances in photonic integrated circuit technology have provided a new platform for compact integrated lasers with large output powers, frequency-agile tuning, and narrow linewidths. For instance, lithium niobate extended-DBR lasers can yield output powers in the tens of mW, GHz-level tuning ranges, and tuning rates in the hundreds of MHz. However, noise levels achievable in other integrated laser designs remain challenging to reach. Here, we address this challenge by implementing extended-DBR lasers in lithium tantalate, thereby achieving intrinsic linewidths as low as 24 Hz, output powers of 10 mW, with tuning features on par with those of lithium niobate. The extended-DBR laser is assembled with modern packaging solutions to improve its robustness and demonstrate long-term stability with a free-running frequency drift within a range of 232 MHz over 19 hours. These benefits, in conjunction with lithium tantalate's suitability for volume manufacturing, promise to considerably expand accessibility to a new generation of widely tunable and low-noise integrated lasers.

Battery energy storage systems (BESS) paired with rooftop photovoltaics (PVs) can deliver measurable cost savings under time-of-use (TOU) electricity tariffs; however, the relative performance of model-based and model-free dispatch strategies remains insufficiently benchmarked on full-year, real-world commercial datasets. This paper presents a full-year (2023) comparative evaluation of three BESS dispatch approaches using data from a commercial PV installation operating under a TOU tariff. The examined strategies include: (i) a mixed-integer linear programming (MILP) formulation with perfect foresight, providing an oracle performance benchmark under the assumed model; (ii) a model predictive control (MPC) scheme based on a day-ahead persistence forecast, representing a low-complexity deployable approach; and (iii) a soft actor-critic (SAC) deep reinforcement learning agent trained under causal information constraints. The MILP benchmark achieves an annual cost reduction of 24.6\% relative to a no-storage baseline. The persistence-based MPC approach recovers 99.2\% of this benchmark using only prior-day data. In contrast, the evaluated SAC agent yields an annual cost higher than the no-storage baseline. This outcome is analyzed in the context of known challenges in reinforcement learning for energy systems, including limited observability and reward design. Overall, the results indicate that, for the studied dataset and tariff structure, persistence-based MPC captures nearly all achievable economic benefits under practical deployment constraints, whereas the considered RL configuration does not yield competitive performance under the same information limitations.

Hierarchical orchestration, in which a Manager agent reviews worker output and can send it back for revision, is the default coordination pattern in production multi-agent LLM frameworks. Classical organizational theory predicts that the authority link speeds convergence on decisive output; work on sycophancy and Degeneration-of-Thought predicts that authoritative critique makes LLM output worse. Prior comparisons vary whole frameworks on tasks with checkable answers, leaving the authority link untested on open-ended work. We present a paired experiment that holds five LLM agents, their roles, prompts, tools, models, and data fixed and varies one link: whether the Manager may reject a worker's output and oblige a revision. Across 43 paired products and 86 runs of a business-intelligence reporting task, a five-model judge panel and a deterministic specification check score every report. The flat organization scores higher on Utility (d = 0.42, p = 0.009) and on Writing Clarity (d = 0.34, p = 0.030); the classical prediction fails. The reports are the same length, but hierarchical reports hedge 53% more, each revision loop is associated with a 0.14-point drop in Writing Clarity, and the hierarchical Writer's first draft is indistinguishable from the flat report: the gap opens inside the revision loop. Specification accuracy is at ceiling in both organizations, and the supervisory tier costs 51.5% more tokens for no quality gain. A supervisor pays for itself when it can verify and becomes a liability when it can only opine.

Hip exoskeletons may improve recovery from unexpected gait perturbations, yet personalizing assistance remains difficult because balance is multidimensional and human-in-the-loop experiments are small-sample and noisy. We present a participant-specific composite balance cost that integrates seven biomechanical sub-metrics spanning margin of stability, center-of-mass dynamics, and whole-body angular momentum. The sub-metrics are converted to direction-aligned, dimensionless cost features, and nonnegative fusion weights are learned on the simplex. Coupled with an empirical-Bayes hierarchical model, the learned-composite selector estimates each tested condition's posterior probability of being best, P(best), and a high-probability candidate set with size $K_{0.8}$. The framework was evaluated with three participants walking at 1.1 m/s during unilateral belt-slip perturbations across 46 hip-assistance conditions. In the full-budget analysis (B = 4 repeats per condition), the selector concentrated 80% of the posterior probability within 1 to 5 of 46 conditions, compared with 2 to 12 for equal-weight fusion and 4 to 37 for principal component analysis fusion. This smaller candidate set could shorten personalization experiments and limit participants' exposure to repeated perturbations in future studies. Selected-condition trials showed lower observed composite costs than no-torque trials, with nominal p < 0.05 for P2 and P3. Leave-one-repeat-out refits yielded positive mean held-out rank correlations for all participants and moderate stability of the learned weights and candidate sets. These proof-of-concept results support participant-specific composite balance evaluation for candidate selection in perturbation-based human-in-the-loop experiments.

Uncrewed Aerial Vehicle (UAV)-assisted Mobile Edge Computing (MEC) is a key technology for future 6G networks, providing wide coverage and flexible computing services. However, the limited resources of UAVs and the dynamic changes in the network structure make it difficult to maintain high efficiency. Existing methods often ignore the semantic information of tasks and the complex relationships among UAVs and mobile terminals, resulting in poor coordination. This paper proposes a joint optimization framework for task offloading, task migration, and trajectory control in semantic communication-enabled multi-UAV edge computing systems, aiming to maximize semantic similarity while minimizing task latency and system energy consumption. To tackle the resultant problem, we develop a Heterogeneous Graph Attention Network-based Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (HAN-MATD3) algorithm. Specifically, we use a heterogeneous graph to model the network topology and apply HAN to extract important semantic features. These features are then integrated into the MATD3 framework to support joint optimization.

In an integrated sensing and communications (ISAC) system, targets may intercept information. We address this specific security issue in a full-duplex ISAC system with malicious eavesdroppers aiming to intercept uplink (UL) and downlink (DL) communication exchanges between the dual-functional radar and communication base station and legitimate communication users. We formulate an optimization framework to maximize the sum secrecy rate for both DL and UL, considering power budget constraints for sensing and communications. The optimization problem is non-convex, so we introduce an iterative joint Taylor-block cyclic coordinate descent (IJTB) method to approximate it as a convex problem. The IJTB method alternates between sub-problems: one for UL beamformers and another for UL power allocation, artificial noise covariance, and DL beamforming, using Taylor approximations to simplify optimization. Simulations demonstrate the effectiveness of our approach compared to standard benchmarks.

Large language model (LLM)-based database migration is often treated as direct code transformation, although enterprise Oracle systems contain heterogeneous SQL and PL/SQL artifacts with different dependencies, execution order, complexity, and validation needs. This paper proposes a hybrid dependency-aware framework that identifies migration tasks, builds a cross-file dependency graph, condenses cyclic dependencies, and uses task specifications to generate specialized migration agents at runtime. The deterministic path combines ANTLR-based parsing with typed dependency extraction, while an LLM fallback is invoked only for units that cannot be parsed reliably. On a corpus of 116 Oracle files, the pipeline produced 1,037 units with zero coverage gaps and 1,271 AST-derived dependencies. The fallback processed 165 parse-error units, recovered 496 additional validated dependencies, eliminated unresolved-dependency units, and increased resolved internal edges from 446 to 527. The graph contained four dependency-respecting phases, while cycle handling was validated separately using Tarjan SCC condensation. A complementary experiment on 1,006 PL/SQL files regenerated 623 scripts (~62%), of which 380 (~61%) executed successfully in PostgreSQL 16. Tables achieved about 85% regeneration success, whereas no query regenerations succeeded under the evaluated specification-mediated baseline, and procedural objects remained strongly dependent on schema context. These results motivate dependency-aware context delivery, task-specific validation, and differentiated agent routing. The paper also formalizes task-to-agent mapping, introduces monitoring and diagnostics for execution feedback, and defines a controlled comparison of monolithic, static-decomposition, dependency-aware, and dynamically orchestrated migration strategies.

Passive photonic structures offer a potential route toward reservoir computing by exploiting intrinsic optical propagation, delay, interference, and memory effects for temporal information processing. This work investigates whether a chirped Bragg grating (CBG) can exhibit fundamental physical properties relevant to a passive photonic reservoir. Rather than presenting the CBG as a complete reservoir computer, the study provides an early proof-of-concept assessment based on experimentally measured device characteristics. Wavelength-dependent group delay and reflection coefficient measurements obtained from a silicon photonic CBG are incorporated into a distributed delay model in which multiple delayed contributions form the reservoir states. The resulting system is examined with respect to distributed delay, fading memory, temporal mixing, and memory capacity using a linear readout based on the standard memory capacity formulation. The results demonstrate that the measured CBG response provides a distributed temporal memory over the experimentally observed delay range and produces temporal mixing through the superposition of multiple delayed contributions. The memory capacity analysis further indicates that past input symbols can be reconstructed from the distributed delay states, providing quantitative evidence of temporal information retention in the measured CBG response. These results suggest that a passive CBG possesses several physical characteristics relevant to reservoir computing and may therefore provide a simple photonic substrate for reservoir-like temporal processing. The study is intended as an initial proof-of-concept, providing a foundation for future experimental and task specific investigations of passive CBG-based photonic reservoirs.

Swift electrons in scanning transmission electron microscopy transfer both linear and angular momentum to nanoparticles, underlying electron-beam-driven nanoscale manipulation ("electron tweezers"). Prior theory relied either on the small-particle (dipolar) approximation, valid only well below experimentally relevant sizes, or on frequency-integrated multipolar calculations that leave the spectral structure of the interaction unresolved. Here we present a fully retarded, causal, multipole-converged electrodynamical methodology for the angular momentum transfer from a swift electron to an isolated spherical nanoparticle, based on a closed-surface Maxwell stress tensor formulation whose angular integrals reduce analytically to a small, material- and trajectory-independent set of irreducible integrals over associated Legendre functions. This lowers the cost of the double multipolar sum from O(l_max^4) to O(l_max^3), enabling convergence up to l_max=51 for nanoparticles as large as a=50 nm, nearly four times the order of the largest previous calculation at this size and previously unreached for an optically complex material, at three to four orders of magnitude lower cost. Applied to aluminum and gold nanoparticles up to a=50 nm, the method resolves the transfer's spectral density across the full frequency domain, showing it is set by interference between the electron and scattered fields, dominating at essentially every frequency; the electric contribution exceeds the magnetic one by two to three orders of magnitude, though spectral resolution reveals sign changes in the magnetic term hidden in the frequency-integrated transfer. At a=50 nm, gold transfers substantially more angular momentum than aluminum despite its more intricate response, by a factor growing with velocity from about 2x at v=0.5c to more than 6x as v->c (fixed b=51 nm from the nanoparticle center).

This is a position paper. We demonstrate that recursive self-improvement (RSI) large language model (LLM) agents are a natural search engine for dynamic model identification of inverter-based resources (IBRs) whose internal controls are often proprietary and hidden from grid operators. White-box models provide physical transparency but require vendor disclosure; black-box models avoid this requirement but sacrifice interpretability; and existing grey-box approaches, including sparse and symbolic regression, are poorly suited to discovering feedback control architectures or incorporating control-engineering priors. Our position is that this gap can be alleviated by (1) restricting the search space to a typed vocabulary of standard control modules, including PI controllers, phase-locked loops (PLLs), low-pass filters, etc., composed under block-diagram grammar rules, and (2) using an RSI LLM agent to perform program search over candidate block-diagram models, guided by measured frequency-domain admittance data at the point of common coupling (PCC), while fitting the free parameters of each candidate by nonlinear least squares. We instantiate this position by adapting ThetaEvolve, an open-source program-evolution framework supporting in-context evolution and test-time learning, to inverter model discovery. In a proof-of-concept study on a grid-following (GFL) inverter benchmark, the RSI loop reduces the normalized root mean square error (NRMSE) of a naive open-loop model from 0.470 to 0.0435 and identifies a 15-module closed-loop structure that closely resembles the hidden ground-truth GFL controller.

Predicting a user's next POI is a task in human mobility modeling, yet LLM-based approaches focus on semantic reasoning from previous mobility records, while neglecting real-world spatial context. However, human mobility is inherently shaped by spatial cognition, including geographic distance and neighborhood context. This issue is further compounded by prior evidence that LLMs often struggle with spatial reasoning tasks, including distance estimation and geographically biased prediction. To address these limitations, we propose our framework, a multi-agent LLM framework that decomposes next-POI prediction into three stages: Firstly, a Pattern Extraction Agent that captures temporal and categorical mobility patterns from trajectory history; Secondly, a Spatial Reasoning Agent that structures candidate activity choices by combining behavioral preferences with real-world spatial constraints, including geographic distance, road network distance, and neighborhood affiliation; and Thirdly, a Decision Synthesis Agent that integrates behavioral patterns and spatial reasoning for final prediction. Experiments on the NYC benchmark dataset with two LLM backbones show improvements over baseline methods, with up to 493% Hit@1 improvement and 37% relative improvement in Hit@5. Ablations show that combining neighborhood affiliation with distance-based features generally outperforms distance-only settings, and that the Spatial Reasoning Agent plays a crucial role in final prediction by integrating behavioral preferences with real-world spatial constraints, especially for smaller models. Overall, the results highlight the importance of spatial reasoning in mobility prediction. Accurate next-POI prediction requires combining behavioral patterns with explicit real-world spatial constraints, and multi-agent decomposition provides an effective structure for organizing these forms of context.

Semantic collapse, the progressive narrowing of what AI systems generate, has been studied mainly in closed settings, and remedies have targeted models and data. We study it in MOLTBOOK, a social network of interacting AI agents that human users configure and steer. Across 30,076 active agents, output grows less diverse within agents and more similar across them over weeks, yet a minority sustains high novelty. Interviews with users of high- and typical-novelty agents (N=11) associate sustained novelty with three features: users value novelty of itself, they supply broad and distinctive material and revise it when output narrows, and they approach MOLTBOOK as a new agentic world to explore, not a venue to instrumentally exploit. A survey of users of distinctive agents (N=53) confirms these patterns. Communities with more novel agents also show more diverse output from other agents. We discuss interface and policy interventions that could support improved human input.

Surgical tissue manipulation demands precision; however, tool-tissue manipulation force magnitudes under realistic conditions are rarely quantified. To address this gap, we proposed and validated a portable ex-vivo force-sensing platform that measures tool-tissue interaction forces across the skull-brain interface during simulated neurosurgery. The system involves fresh calf brain tissue, used as a biological surrogate for brain parenchyma, placed in a 3D-printed human skull model equipped with a 6 degree-of-freedom force/torque sensor and a real-time data acquisition system. Five validation protocols assessed the accuracy and dynamic fidelity of the platform against ground-truth measurement, static accuracy and linearity using calibrated weights (0.5-50 g), minimum detectable force, spatial consistency across different anatomical regions, effect of surgical draping, and long-duration stability. Across protocols, measured forces showed excellent agreement with reference loads (correlation R = 0.9997), with RMSE < 0.005 N and mean relative error under 2%. The platform reliably detected low-magnitude forces down to 1 g (9.8 mN), while surgical drapes introduced no meaningful signal distortion and prolonged recordings exhibited minimal drift. Overall, the proposed framework provides objective, high-fidelity force quantification for skill training and performance assessment using fresh calf brain tissue and may serve as a foundation for force-based evaluation across other surgical procedures. Future work will integrate clinically used surgical instruments to increase procedural realism and will progress toward clinical trials to evaluate usability, educational impact, and translational relevance in practice-adjacent settings.

Software-defined vehicular networks (SDVNs) under high mobility and fluctuating traffic demand offer programmable, centralized control for latency-sensitive intelligent transportation systems. However, data-plane Quality of Service (QoS) is often degraded by control-plane overload due to frequent handovers and dense vehicle-to-infrastructure (V2I) contacts. To address this, we propose two lightweight mechanisms for low-latency control-plane resizing in multi-controller SDVNs. The first - \textit{Control-plane Centric Control-plane Resizing Mechanism} - proactively offloads roadside units from overloaded controllers to underloaded or idle ones when a predefined load threshold is exceeded, preventing prolonged overload with minimal decision latency. The second - \textit{Data-plane Centric Control-plane Resizing Mechanism} - triggers resizing based on observable data-plane QoS degradation, such as average round-trip time exceeding a QoS threshold, aligning control-plane adaptation with V2I service experience. Both mechanisms are implemented and evaluated on Mininet-WiFi emulation testbeds with realistic worst-case vehicles mobility. Compared to fixed single-controller and static multi-controller benchmarks, the proposed algorithms significantly reduce end-to-end delay and packet loss while improving load balancing rate.

Hamilton-Jacobi (HJ) reachability provides a principled framework for synthesizing safety certificates and robust controllers for safety-critical robotic systems. However, applying reachability analysis to high-dimensional nonlinear systems remains challenging: classical grid-based solvers suffer from the curse of dimensionality, continuous-time neural solvers require accurate spatial value gradients, and reinforcement-learning-based approaches often suffer from weak boundary anchoring and non-stationary adversarial policy optimization. We propose a discrete-time neural reachability framework for control-disturbance-affine systems that learns backward reachable tubes (BRTs) and backward reach-avoid tubes (BRATs) through Bellman-Isaacs value propagation. Our key idea is to combine equation-driven self-supervision with structured policy learning: rather than computing explicit PDE-gradients, we exploit the bang-bang structure of optimal safety interventions to construct approximate teacher actions from gradient-free value probes, converting adversarial actor learning into supervised policy learning. To stabilize long-horizon value propagation, we leverage the learned actor to train the value function backward from the terminal boundary using a windowed temporal curriculum, where each window is used as the boundary condition for the next window. Across benchmark problems up to 80 dimensions, our method learns accurate reachability value functions while improving stability over existing learning-based solvers. We further demonstrate observation-space scalability on F1-tenth racing with over 16,000-dimensional egocentric inputs. The learned safety filter generalizes zero-shot to unseen tracks and transfers to a physical RC car, achieving real-time robust collision avoidance.

This paper addresses secure leader-follower formation of unknown nonlinear multi-agent systems under actuator constraints, external disturbances, and false-data-injection (FDI) attacks. The graph-coupled coordination-error dynamics are formulated as local zero-sum differential games, where a nonquadratic input utility yields saturation-compatible secure policies and actuator-channel FDI and disturbances act as adversarial inputs. To eliminate explicit dependence on the unknown nonlinear drift, an integral Bellman-Isaacs identity enables critic-only learning from finite trajectory data. A two-power state-cost structure and a deadline-parameterized critic update connect optimal learning with predefined-time stabilization. Unlike fixed-time methods whose settling-time bound is determined by preselected gains, the proposed framework assigns the overall deadline first and allocates it among data informativity, critic learning, the reinforcement window, and formation convergence. Practical predefined-time convergence of the critic and formation errors to bounded residual sets is established independently of initial conditions, while secure actuator constraints are satisfied by construction. Simulations validate the framework under FDI attacks, disturbances, input constraints, and different initial conditions.

Diffusion-based generative models (DMs) have found applications in control problems, and in particular robotics, where the DMs enable exploration of possible control solutions. A critical shortcoming of these applications is that they have lacked optimality guarantees. This is a problem for their potential use in fuel-optimal spacecraft trajectories that are characterized with long time-horizons and bang-bang profiles. Alternatively, indirect optimal control methods ensure explicit satisfaction of necessary conditions, but are highly sensitive to the initial costate estimation needed to solve the resulting Hamiltonian boundary-value problems (HBVPs). To alleviate this sensitivity and enlarge the convergence domain of HBVPs, advanced indirect methods have been developed that use smoothing approaches and continuation. We propose a diffusion-based multiple shooting indirect control method that combines the exploration capability of DMs with indirect method to generate fuel-optimal spacecraft trajectories. We benchmark our method against an advanced indirect method on a fuel-optimal Earth-Mars low-thrust transfer problem, showing higher convergence robustness than the advanced indirect method that is based on random costate initialization. Code and visualizations are available at https://saeidtafazzol.github.io/Diffusion_Indirect_Control/.

Large language models (LLMs) are increasingly used in specialized university courses, but control-systems questions require coordinated terminology, notation, derivations, and stepwise explanations. Direct general-purpose responses may be inconsistently structured and hard to verify. Using exercises and reference solutions from a Linear Control Systems course, we built a supervised fine-tuning dataset of 360 system-user-assistant conversations. We applied LoRA to Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct. With identical data splits, inference settings, and evaluation protocols, we compared base and fine-tuned models and tested LoRA ranks r=4, 8, and 16. Evaluation used ROUGE, BERTScore, and structured-output features to measure reference-answer similarity and stability of the Solution-Method-Teaching Points format. LoRA improved both similarity and structured-output stability at both sizes. On the current test set, 7B-r16 achieved the highest ROUGE-L (0.4093) and BERTScore-F1 (0.8643), while r=8 offered a better balance between performance and parameter efficiency. Bootstrap resampling showed ROUGE-L gains of 0.0764 [0.0613, 0.0915] for 3B-r16 and 0.0874 [0.0687, 0.1042] for 7B-r16; both intervals exceeded zero, indicating stable textual-similarity improvements on the current test set. These results suggest LoRA can align open-source instruction-tuned models more closely with the language and pedagogical organization of course reference answers. However, the metrics mainly capture textual similarity and formatting consistency, not domain-specific reasoning or mathematical correctness, which require expert assessment and task-specific rubrics.

Real-time characterization of refractive index (RI) dispersion is pivotal for advanced optical sensing, yet conventional surface plasmon resonance (SPR) platforms are bottlenecked by the narrow bandwidth of noble metals (Au, Ag) and the mechanical instability of sequential scanning. Here, we report a novel Al-based parallel SPR platform that overcomes the bandwidth and temporal constraints of conventional noble-metal systems. Leveraging the unique low-loss broadband response of Al, enabled by the suppression of interband transitions, we engineered a system for simultaneous excitation at 450, 520, and 635 nm. By integrating spectral-angle multiplexing with RGB-channel demultiplexing on a CMOS camera, the platform achieved acquisition of dispersion profiles without mechanical motion. Validated against NaCl solutions, the system demonstrates metrological accuracy and exceptional agreement with Cauchy dispersion models. The proposed architecture eliminates temporal drift and vibration errors, establishing a new benchmark for real-time dispersion characterization. By decoupling sensing from mechanical constraints, this work pioneers a compact, robust framework for next-generation, field-deployable sensors capable of distinguishing complex analytes via their unique spectral signatures.

Multi-agent systems for code generation are deployed with a single communication topology, chosen once for every problem. This is the wrong granularity. Evaluating five topologies on 614 problems from APPS, HumanEval+ and LiveCodeBench, we find that the advantage of hierarchical collaboration over a single agent grows from 2.4 points of pass@1 on the easiest third of problems to 21.1 points on the hardest third, while its token cost stays about ten times higher. We propose the Difficulty-Aware Topology Selector (DATS), which predicts each topology's probability of solving a problem and selects the one maximising predicted success minus cost. Its predictor is a graph network that treats the five topologies as nodes of a connectivity order rather than independent labels, worth 1.7 points over a flat multi-label head. Because the cost penalty is a single scalar recalibrable without retraining, routers compare at equal spend: under this budget-matched protocol six cost-aware methods span 21.6 percentage points, and two baselines leading DATS fall behind once calibrated to it. Fixed at 40% of the always-hierarchical cost, DATS reaches 77.7% pass@1 against 73.6% (always-hierarchical) and 74.3% (strongest learned competitor), all eleven pairwise McNemar comparisons surviving Holm-Bonferroni correction. The 4.1-point gain holds across four backbones spanning fourteen points of capability, and replacing the 39 interpretable features with a graph network or a pretrained encoder shifts accuracy by at most 1.3 points, never significantly. A cross-domain study on 400 mathematical reasoning problems reproduces the effect, the gap widening from 2.5 to 20.9 points.

Automatically recognising a fabric's construction (jersey, twill, satin) is a bottleneck in textile sourcing, where incoming swatches are still typed by hand. Benchmark accuracy suggests the problem is solved, yet rarely survives deployment. On the \numClasses{}-class FabricFlow benchmark we expose three gaps that headline accuracy hides. First, a duplication audit reveals train/test leakage that inflates accuracy; we rebuild leakage-free splits that report the true difficulty. Second, on the clean data the binding failure is acquisition-source shift between catalogues, not the peripheral shortcuts one might fear: on an archive-exclusive hold-out, standard training holds 58.0\% Top-1 at a calibration error of 0.158, while a simple, architecture-agnostic central-texture recipe adds 13.5 Top-1 points and restores calibration. Third, because confusing one fabric family for another is costlier than a within-family slip, we optimise a taxonomic-severity cost: a confidence-gated routing policy auto-types confident swatches and refers only the uncertain minority to a human, sharply cutting onboarding cost. Throughout we report honest negatives: hierarchical classification, OCR fusion and zero-shot vision--language models all fail to help, yielding a concrete, calibrated, cost-aware recipe for deployable textile onboarding.

This paper studies how a feedback law synthesized directly from data can be realized by spiking control while retaining a game-theoretic performance guarantee. We consider distributed $\varepsilon$-Nash equilibrium (NE) seeking in network games played by linear dynamical agents with unknown models and exogenous disturbances. The pseudo-gradient of the game is treated as a regulated error, and local internal models account for signals generated by known exosystems. Robust linear matrix inequalities are then used to compute stabilizing analogue feedback gains directly from noisy local input-state data, without identifying the agent dynamics. To implement these gains using only fixed-weight spikes, we develop two spiking realizations. The first realization uses non-interacting leaky integrate-and-fire units, while the second permits reset coupling among the neuronal units. In both cases, a continuous auxiliary coordinate exposes the impulsive closed loop as the stable analogue system driven by a bounded implementation error. This representation yields forward completeness, Zeno-freeness, and an ultimate bound on the pseudo-gradient, subject to explicit event-processing conditions for the connected architecture. The bound implies that, after a finite transient, the agents' outputs constitute an $\varepsilon$-NE for every $\varepsilon$ above a finite threshold. A spacecraft formation reconfiguration example illustrates the data-driven synthesis, the two spiking realizations, and their practical equilibrium behavior.

Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider-neutral benchmark for fidelity to a versioned, update-governed identity contract. It separates recall, composition, behavioral enactment, resistance, persistence, lineage, and role-conditioned updates while keeping scoring oracles outside the target process. Two frozen campaigns cover sixteen synthetic profiles, thirty-two probes, and three independently initialized target configurations, yielding 1,536 retained responses. A judge-independent literal audit finds direct-parent identifiers in 48/48 atomic responses but only 1/48 implicit self-portraits. On eight profiles, explicit field cues increase joint presence of three identity identifiers from 0/8 to 7/8 under the same four-sentence instruction. A separate startup body-label substitution increases full-designation presence from 1/8 to 7/8 while parents remain absent. These contrasts reveal prompt-dependent component selection and component-specific sensitivity to startup cues in the tested deployments. Replaying identical factorial responses also yields a Claude headline mean 12.5 percentage points below Astra's, demonstrating evaluator sensitivity separately from target behavior. The studies use single target samples per condition, with post-hoc audits and follow-ups. PAI-Bench provides a reproducible evaluation protocol for measuring factual availability, identity expression, and behavioral enactment as distinct aspects of identity-contract fidelity.

Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database querying, key performance indicator (KPI) analysis, demand forecasting, and performance diagnosis require heterogeneous expertise spanning data engineering, operations research, and domain knowledge. In this work, we propose an agentic system for supply chain analytics that bridges the gap between business decision-making and technical expertise, where a coordinator agent interprets user intent and delegates sub-tasks to specialized agents. The system supports both exploratory analysis and deterministic workflows, enabling planners to transition between ad hoc questions and structured processes. Domain logic is encapsulated within specialist agents and prompts, yielding a scalable, modular, and auditable design and lowering the cost of functional extension through prompt-centric development. We evaluate the proposed architecture on a test environment that replicates multi-echelon inventory management operations. Results show that our multi-agent design achieves a 90\% accuracy, which is competitive with a single agent baseline while reducing input token usage by roughly fourfold, substantially improving scalability and cost-efficiency. Furthermore, we provide case studies to demonstrate interpretable suboptimality detection and automated forecast optimization, illustrating how agentic architectures can effectively combine open-ended exploratory analysis and deterministic supply chain analytics workflows, and provide a practical pathway toward more accessible and extensible decision-support systems.