Physical AI Brief

We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects. The goal is to represent the scene as a collection of individual object meshes placed in a shared world frame, as required by downstream applications such as gaming, AR/VR, simulation, and robotics. This task is challenging in densely cluttered scenes, where objects heavily occlude one another and each view reveals only a fraction of their geometry. Geometry-based approaches typically reconstruct the scene as a single representation and leave incomplete geometry in occluded regions, while existing compositional methods with generative priors are largely limited to relatively simple scenes. We show that complex scenes with hundreds of objects can instead be generated compositionally by adapting a strong single-object 3D generative prior to multi-view observations. We instantiate this paradigm with Pixal3D, extending it with a multi-view conditioning pathway that grounds object generation in multiple posed observations. Although the model is finetuned entirely on single objects in canonical space, it generalizes to large scenes with severe occlusion without any scene-level training, demonstrating the feasibility and scalability of this paradigm. We further introduce UE-MeshyScene, a photorealistic benchmark of densely cluttered scenes with hundreds of objects, per-object annotations, and ground-truth meshes. Across single-object, controlled multi-object, and UE-MeshyScene evaluations, our method consistently outperforms prior approaches, with larger gains as scene complexity and occlusion increase. Finally, we demonstrate broader applicability by converting generated 3DGS worlds, such as Marble and HY-World 2.0, into compositional mesh scenes.

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms: (1) a graph-aware attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian; and (3) a global topological conditioner attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing benchmarks rarely evaluate whether AI systems can reason over a real user's longitudinal wearable record. We introduce WearableQA, a benchmark comprising 4,084 10-option multiple-choice questions constructed from the wearable time series, blood biomarkers, and demographics of 200 real users, each with up to 500 days of daily measurements. WearableQA preserves authentic wearable distributions that include device noise and inter-individual variability. To evaluate distinct reasoning capabilities, we introduce 16 question types organized along two complementary axes: data versus health reasoning, which distinguishes computation over longitudinal measurements from physiological interpretation; and single- versus cross-signal reasoning, which separates reasoning about individual signals from the integration of multiple signals. To construct reliable questions at scale, we adopt a dual-grounding framework that combines literature-grounded physiological findings with statistically validated population-grounded physiological patterns. This enables the capture of meaningful relationships observed in real-world wearable data. Evaluation of 14 proprietary and open-source LLMs demonstrates that WearableQA effectively differentiates model capabilities, with performance ranging from 19.6% to 72.9% against a 10% chance baseline. Moreover, WearableQA remains far from solved: most models achieve accuracies below 60%. Overall, WearableQA provides a realistic and diagnostic benchmark for evaluating LLM reasoning over real-world wearable data.

Diffusion TV is an interactive AI art installation that offers a tangible and embodied experience of diffusion models through a modified CRT TV. By physically manipulating the TV's antenna, audiences control the clarity of AI-generated images and sounds, metaphorically enacting the denoising process that underlies diffusion-based generation. Using the tuning knob, participants switch between three channels featuring AI-generated animals from the Past (extinct species), Present (endangered species), and Future (speculative creatures), situating the interaction within a temporal and ecological narrative. Through continuous audiovisual feedback and physical interaction, Diffusion TV foregrounds the generative process over final outputs, allowing audiences to explore intermediate states as experiential material. Rather than providing explicit technical explanation, the work presents an alternative, embodied mode of explainable AI that invites exploratory engagement with and reflection on generative technologies.

Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property. Paraphrasing the instruction alone can substantially change predicted progress scores, and can even flip identical robot behavior between failure and success. To measure this failure mode, we introduce ROBORMBENCH, a benchmark with 2,390 real-robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites. Across proprietary and open-source VLMs, paraphrase-induced instability is widespread and severe, grows under more divergent rewrites, and is not reliably reduced by scale or explicit reasoning. Dedicated reward models trained with trajectory-grounded supervision are substantially more stable. These results show that paraphrase robustness is a core requirement for reliable VLM-based reward modeling in robotics.

More than a decade in, explainable AI (XAI) for computer vision has assembled a mature toolbox: attribution, feature visualization, concept-based, and circuit-based methods. Yet almost all of the field's effort has gone into building and comparing these methods, and little into the question they were meant to answer---how interpretable are our models, and are we making progress as they evolve? We argue for shifting the field's focus from methods to models, along two complementary lines. One is already within reach: existing tools let us characterize and compare what different models represent and compute. The other is harder, and largely neglected: whether a model can actually be understood by the humans who rely on it---the independent evaluators on whom trust and certification depend, not the experts confirming what they already expect. It can only be measured, not inferred. We review why the toolbox is mature enough to support both, survey the thin body of work comparing models, draw a parallel to systems neuroscience, and close with a model-centric XAI agenda.

Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing benchmark measures the gap. We introduce the Korean Open Public API Benchmark (KOPA-Bench), comprising 145 real-world tasks. To close this gap, we present EDGE, an Execution-grounded Dynamic Graph for tool-calling data synthEsis driven by live execution. EDGE builds a graph of how each tool's output can feed another's input, keeps only the links that succeed when actually called against the live APIs, and traverses these verified links to synthesize executable multi-step trajectories. Fine-tuned via GRPO on the resulting dataset, our 9B model nearly matches the untuned 27B model from the same family, improving substantially not only on KOPA-Bench but also on the BFCL benchmark.

Visual reasoning tasks require a system to jointly perceive visual content and apply formal relational constraints---a combination that neither pure neural nor purely symbolic approaches handle well in isolation. This paper proposes a Neuro-Symbolic (NeSy) framework that closes this gap by tightly coupling a Vision-Language Model (VLM) for automatic First-Order Logic (FOL) rule induction with a Dynamic Logic Tensor Network (D-LTN) for differentiable rule verification, in a closed iterative feedback loop. The VLM receives a small set of labelled visual examples and proposes candidate FOL rules conforming to a strict grammar (Think); the D-LTN is automatically assembled from these rules at runtime and evaluates them grounding on CNN-produced visual embeddings (Verify); and verification failures are fed back to guide the VLM's next hypothesis (Revise). Evaluated on the ViSudo-PC benchmark across four visual domains (MNIST, EMNIST, KMNIST, FMNIST), the system induces valid Sudoku constraint rules using only three training examples as visual context. The proposed method achieves AUC scores matching or outperforming previous methods (NeuPSL, LTN), showing the potential for automatic rule discovery through VLM. Code is available at https://github.com/homayoun-afshari/nesy.

LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a system, diagnose errors, or decide when to escalate an output. Such use assumes that the explanations agree with the component's observable decision behaviour. We test two interpretations of the named factors: necessity, meaning that changing a factor would change the output, and sufficiency, meaning that retaining it while removing other changeable information would preserve the output. We evaluate these interpretations in two synthetic use cases: recommending advisors to clients and judging prompts for harmfulness or risk. Models return an output and the top three factors that most influenced it. Controlled black-box interventions estimate a necessity score for each factor by measuring how often changing it changes the output, and a sufficiency score by measuring how often retaining it preserves the output. Across eight models from the Claude, GPT, and Gemini families, the mean Spearman correlations between the cited ranking and the necessity and sufficiency scores are 0.349 and 0.354 for advisor recommendation, and 0.431 and 0.580 for prompt monitoring. Furthermore, an uncited factor scores above the lowest-scoring cited factor in 57.6% of advisor responses under necessity and 58.1% under sufficiency; the corresponding prompt-monitoring rates are 25.8% and 8.9%. The cited top three contain useful information but do not reliably identify the three factors with the strongest measured influence under necessity or sufficiency. The framework provides a black-box reliability check for explanations used in agent oversight while remaining scoped to individual LLM decisions.

Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy cannot distinguish a model that predicts a property from one that retrieves a published number. We audit 22 frontier models on 12 regression benchmarks for verbatim retrieval and find that it is widespread but relatively benchmark-specific: on five datasets more than $50\%$ of the LLMs show verbatim retrieval, while on the remaining datasets it appears only in isolated cells. We run our experiments at two reasoning levels and find that reasoning changes retrieval. The same experiments, on the same molecules and with the same prompt, are flagged $89\%$ more often at the higher reasoning level than at the lowest one. Finally, we test a way to interrupt retrieval in our most contaminated cases, and find that the strongest models in some cases still recognise a combination of transformed SMILES strings and original labels. Furthermore, suppressing retrieval moves the prediction errors of the different models closer together in relative terms, while their differing use of verbatim retrieval spreads them apart. This indicates that the general predictive capability of an LLM is not determined solely by the amount of memorised values. This work provides an overview of the amount and depth of verbatim retrieval in molecular regression benchmarks using LLMs.

Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a problem of conditional visual grounding: the visual target required for successful control changes with the manipulation phase and, in more complex tasks, with the observed task state. Using Action Chunking with Transformers (ACT), we systematically introduce distractor objects and receptacles with controlled color and shape similarity and localize failures to picking and placement. We find that distractor sensitivity is specific to both the type of visual similarity and the manipulation stage. Guided by this diagnosis, we evaluate distractor augmentation, phase-dependent attention regularization, and appearance-based visual prompting as complementary interventions for improving target selection while preserving spatial information required for control. These interventions substantially improve robustness in simulation and on a physical UR3e. We further examine the same failure pattern in a pretrained vision-language-action policy on a state-conditioned instrument-handling task, where the observed state of a medical instrument determines the correct destination. Together, the results show that visual distractors can cause incorrect object or destination selection even when the underlying manipulation skill remains intact, and that explicitly improving target selection can substantially recover performance across distinct visuomotor policy-learning regimes.

Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combining visual-state inspection with precise, high-throughput command-line operations, so capable agents must coordinate both modalities over shared application state. Yet scalable hybrid environments remain scarce because supporting both GUI and CLI over real applications typically requires substantial manual engineering for each application. Existing agents also struggle to use the two interfaces complementarily: CLI-native agents lack visual perception for tasks involving interface state or layout, while GUI-native agents are inefficient for operations better executed through commands. We introduce CUA-Universe, a scalable environment-to-data pipeline that turns real desktop software into hybrid GUI+CLI environments. App-Forge adapts applications into reproducible VMs and command-line surfaces it discovers, wraps, or generates, scaling to 16 applications; Task-Weave synthesizes diverse hybrid tasks of controllable difficulty from reusable operations over seed files; and Path-Steer steers rollouts along efficient hybrid paths and harvests verified trajectories for post-training. Training on this data shifts behavior from inefficient GUI interaction and brittle CLI scripting toward effective GUI+CLI orchestration. Our 9B model improves both success and efficiency on CUA-Verse (Score +39.3 pts; -37% steps, -60% tokens), OSWorld (SR +16.8 pts; -57% steps, -44% tokens), and OSWorld-MCP (Score +7.84 pts; -27% steps, -30% tokens). CUA-Universe provides a scalable path toward more capable and efficient computer-use agents.

Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task state, dependency-aware reasoning, conditional decisions, and reliable grounding. We investigate a neuro-symbolic framework that combines learned VLA control with explicit task graphs and multimodal procedural memory. Task graphs encode action dependencies, valid transitions, and branch conditions, while memory maintains the active step, completed actions, textual context, and task-relevant visual evidence. Together, these structures guide object selection, destination grounding, subgoal dispatch, and verification of expected state transitions. Human demonstrations provide additional spatial and temporal guidance through gaze or saliency cues. To isolate their effect on policy learning, our initial study bypasses cross-view gaze transfer and directly annotates pseudo-gaze in robot-view teleoperation videos. The resulting guidance is used during VLA fine-tuning and inference. We study two long-horizon manipulation domains, workspace clearing and surgical-instrument handling, which require ordered execution, visually grounded decisions, and conditional branching. We evaluate correct-object and destination selection, subtask completion, task progress, step-order consistency, complete-task success, and procedural or execution mistakes. This work positions structured symbolic reasoning and demonstration-derived visual guidance as complementary mechanisms for reliable long-horizon VLA manipulation.

Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large language models (LLMs) can reason about such distinctions, but applying them directly to hundreds of millions of product pairs is operationally impractical. We introduce a two-level framework that distills LLM reasoning into an efficient non-generative student and adapts its decision boundary to product-type-specific trade-up criteria. At Level 1, a retrieval-augmented few-shot LLM teacher generates structured relation labels and natural-language rationales. These rationales supervise a compact embedding-pair classifier through alignment and contrastive objectives; at inference, the student uses only two precomputed 768-dimensional product embeddings, with no LLM calls or text generation. On a fixed human-annotated benchmark of 8,352 pairs, a 15.5M-parameter four-class reasoning-distilled student achieves AUC 0.924 (95% CI [0.918, 0.929]), compared with 0.912 for the four-class label-only student. At Level 2, product-type test-time training (PT-TTT) uses few-shot demonstrations to optimize lightweight category-specific adapters over the frozen student. PT-TTT improves AUC from 0.924 to 0.941 and average precision from 0.920 to 0.940. On a 100K-pair proxy catalog, the distilled student on a single eight-GPU machine is approximately 5,000x faster and 10,000x lower in estimated cost than direct LLM inference.

Human-robot interaction (HRI) enables intuitive and intelligent collaboration between humans and robots in real-world environments. This paper introduces a humanoid robot prototype designed as a flexible testbed for developing and integrating artificial intelligence (AI) modules in HRI tasks. The system features a 12 degree-of-freedom (DOFs) dual-arm mechanism and a 2 DOFs head with an expressive LCD screen to express facial emotions. All hardware components are controlled by a custom-designed controller board with real-time AI processing supported by an onboard Jetson module. The system incorporates three AI modules: (1) gesture recognition using MediaPipe Pose and an LSTM classifier, (2) object detection with YOLO and 3D localization, and (3) voice-command processing through speech recognition and large language model(LLM)-based semantic parsing. The platform is validated through experiments on positioning accuracy, with results showing average manipulation errors of approximately 1.83 cm. To demonstrate its versatility, experimental results show over 90% task accuracy, with gesture recognition reaching 96%, speech recognition reaching 92%. The results confirm the effectiveness of the proposed system as a reproducible and accessible humanoid platform for research and prototyping in HRI.

This paper develops a calibrated transient forecasting surrogate model for generator digital twin (DT) decision support that evaluates planned active- and reactive power load commands before they are applied. The proposed event-conditioned Hankel Dynamic Mode Decomposition with Control (Hankel-DMDc) model combines delay-coordinate lifting, command-event memory features, and an event-weighted Hankel basis so that sparse load-transition dynamics influence the reduced representation and fitted dynamics. This design targets intervals where voltage/frequency deviations and recovery behavior determine whether a candidate load command keeps the system within acceptable limits. To provide operator-facing confidence information, a split-conformal calibration layer is applied to the frozen surrogate model to form event-conditioned joint prediction bands for voltage and frequency. The experimental results show event-window root-mean-square errors of 1.058 V and 0.155 Hz. For a nominal 90% target, the bands attain 90.17% pointwise joint voltage-frequency coverage, with mean band widths of 3.55 V and 0.566 Hz. A 50-s open-loop rollout is computed in 181 ms on a single CPU core, approximately 280 times faster than real time, with forecast accuracy evaluated over horizons up to 5 s. These results demonstrate a computationally efficient advisory framework for generator DTs that combines transient prediction with calibrated uncertainty.

Agent based systems are increasingly deployed in information critical systems including healthcare management systems, and smart grids. In this paper, we consider a multi-agent system where each agent has a latent goal that needs to be kept hidden from observing adversaries. More specifically, this paper studies privacy-preserving consensus in networked multi-agent systems under goal inference attacks. We propose a Trust-Aware Privacy Control framework that adapts message disclosure based on the dynamic trust relationships between agents. The proposed method controls information release using a trust-dependent stochastic policy. This enables a tradeoff between consensus performance and privacy preservation. Experiments demonstrate that the proposed method reduces adversarial goal inference accuracy compared to representative baselines, while maintaining competitive consensus utility, thereby highlighting the effectiveness of trust-aware mechanisms in privacy preservation of the agents in multi-agent systems.

Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only $+0.0004 \pm 0.0020$ following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by $+9.91$ or $-13.28$ percentage points depending on the specific migration direction. In RAG systems, partial embedding migrations using a 50/50 mixed index capture only a 4.96-point accuracy improvement, forfeiting the majority of the 11.90-point gain achieved through full re-embedding. Diagnostic decomposition attributes 80% ($0.467 \pm 0.014$) of the NOTES accuracy deficit to information lost during initial construction, whereas retrieval failures drive 81% ($0.364 \pm 0.012$) of the RAG deficit. Finally, store-only repair of NOTES fails to reach a 90% performance recovery target in all 48 test cases, whereas retaining the raw source history enables successful recovery in 34 of 48 cases for one tested direction. These findings highlight the necessity of direction-specific migration testing, strict embedding space isolation, and the retention of source histories for memory repair.

Generating categorical graphs requires choosing node and edge types that form a coherent structure without depending on node order. Many graph generators encode categories as fixed one-hot vectors, which can impose an artificial geometry in which categories are equidistant. We propose Embedded Graph Flows (EGF), a generative model that learns continuous embeddings for node and unordered-edge categories and transports Gaussian noise towards these learnt endpoints using a permutation-equivariant graph transformer. A terminal readout maps the embeddings back to discrete graph categories. Across molecular benchmarks, EGF achieved competitive performance. On QM9, EGF gives the best result on all four reported metrics among the three methods, including a Fréchet ChemNet Distance (FCD) of 0.150, compared with 0.717 for the categorical-diffusion baseline DiGress and 0.812 for the bridge-based baseline GruM. When applied to larger molecules in ZINC250k, EGF retains the lowest maximum mean discrepancy (MMD) using the neighbourhood subgraph pairwise distance kernel (NSPDK), indicating close agreement with the local substructures of the reference molecules. Our code is available at https://github.com/Trusted-System-Lab/EGF.

Quantum circuits are central to implementing quantum algorithms on quantum devices, where quantum gates must be reversible. Many quantum algorithms rely on Boolean functions, which must therefore be implemented reversibly within quantum circuits. Reversible circuit synthesis provides a way to translate such Boolean functions into reversible circuits. Binary decision diagrams (BDDs) offer a scalable approach to this task, but the resulting BDDs and circuits depend heavily on variable ordering. Existing ordering heuristics commonly minimize BDD size because it is closely tied to the circuit size. However, BDD size is an imperfect proxy for the quantum cost of the synthesized circuit (QCC). We propose \texttt{QuantumEvo}, an evolutionary framework that uses an LLM as a heuristic generator for QCC-aware BDD variable ordering. Instead of predicting orderings directly, \texttt{QuantumEvo} searches over ordering heuristics initialized from multiple heuristic families. Candidate heuristics directly manipulate variable orderings using standard BDD operations and are selected by downstream QCC. The discovered heuristic, HGA-QE, modifies the sifting step inside a genetic algorithm so that the procedure is better aligned with QCC. Across the benchmark set, HGA-QE achieves a 70.9\% tie-or-win rate against the per-function best baseline and is strictly best on 13.5\% of the functions. The results demonstrate broadly competitive QCC performance, with HGA-QE showing a clearer relative advantage in strict wins on the two benchmark suites drawn from sources different from the data used for heuristic discovery.

Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task completion under predefined settings, offering limited insight into model reasoning under increasing spatial and procedural complexity. We introduce \textbf{RoboSPA} (\textbf{Robo}t \textbf{S}patial-\textbf{P}rocedural \textbf{A}ssessment), a large-scale robotic manipulation dataset and benchmark for diagnosing embodied reasoning in VLA models. \texttt{RoboSPA} focuses on two core dimensions, Fine-Grained Spatial Reasoning and Long-Horizon Procedural Planning, covering 10 task categories and 56 base tasks. Each task is instantiated across five difficulty levels, yielding 280 variants with increasing spatial ambiguity and procedural complexity. We collect 527K trajectories across multiple embodiments and diverse scenes. Beyond binary success rate, \texttt{RoboSPA} introduces diagnostic metrics for more detailed evaluation. Experiments on representative VLA models show that current systems still struggle with complex spatial relations, precise low-level execution, and memory-intensive planning. These results establish \texttt{RoboSPA} as a challenging diagnostic benchmark for developing more capable, reliable, and generalizable embodied agents. Our data and code are available at https://github.com/fanzhenxuan/RoboSPA.

Palynomorphs (microscopic, organic-walled fossils such as pollen, spores, and dinoflagellates) are important high-resolution records of past climates and are critical to the study of ancient ecosystems. Existing methods rely on manual analysis of high-resolution, multifocal digital microscopy images, which is slow and time-consuming and requires researchers to compromise on the scale of their investigations. To the best of our knowledge, our work proposes the first ever scalable end-to-end pipeline for automated palynomorph detection in whole slide images that addresses this bottleneck through: (1) efficient methods for decomposing and compressing digitized multifocal microscope slide images into tractable 2-dimensional tiles for analysis; (2) benchmarking modern object detection models, including RF-DETR, for the detection of palynomorphs, achieving an AP@50 of 0.879; (3) an efficient algorithm for the synthesis of detection outputs across large-scale, high-resolution images; and (4) an I/O optimization resulting in faster inference time. Our methods drastically reduce the time required for palynomorph detection in a single slide from often days of manual inspection to under one hour of automated analysis, enabling palynological research at a substantially greater scale.

Deepfake detection models often rely on high-quality inputs, fixed inference paths, and computationally expensive architectures, limiting their use in low-resolution and resource-constrained settings. This paper proposes AdaGate-DF, an adaptive gated deepfake detection framework that uses image-quality cues to route samples through a dual multi-exit system so high-quality images can exit earlier and save compute. We evaluated AdaGate-DF against MaD-CoRN, DefakeHop++, and ShuffleNetV2 on two benchmark datasets (Celeb-DF and FaceForensics++) under multiple configurations to test image resolution dependence and training and inference efficiency. On Celeb-DF, AdaGate-DF achieves an AUC of 0.9370, outperforming MaD-CoRN and DefakeHop++ while maintaining a low inference latency. Resolution-based testing shows consistent improvement as input resolution increases, reaching an AUC of 0.9708 at 384 by 384. The FaceForensics++ results highlight that AdaGate-DF remains effective under class imbalance, following competitive results with evaluated models. Overall, AdaGate-DF demonstrated a practical balance between detection performance, uncertainty-aware prediction, and computational efficiency for variable-quality deepfake detection.

Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures a central pattern in agentic AI: each agent sees only part of the data and passes on only its own conclusion. Their model considers a linear regression problem with the mean squared error (MSE) loss. Agents sit in a DAG and each sees only a subset of the features and its parents' predictions, fits a linear predictor, and passes only its prediction forward. The benchmark is the full-feature learner that sees all raw features. A path of depth $D$ is $M$-covered if every block of $M$ consecutive agents collectively sees all raw features. Kearns, Roth, and Ryu proved that the excess mean squared error of the last agent on such a path is $O(M/\sqrt D)$, and gave a cyclic instance with excess error $Ω(M/D)$ for $D<M^2$. We close this gap: the correct rate is constant up to depth $M^2$, and $Θ(M^2/D)$ beyond it. We first give a sharper analysis of the cyclic instance and improve its lower bound to $Ω(\sqrt{M/D})$ for $D<M^2$. We then construct, for every depth $D\ge M^2$, an $M$-covered path of depth $D$ with excess error $Ω(M^2/D)$. The same instance gives the constant lower bound for all $D < M^2$. We also show that for any fixed distribution the excess error contracts geometrically along the path, ruling out any single instance that witnesses any polynomial lower bound at every depth. Finally, we prove the same optimal rate for logistic classification in the logit-passing model of Bateni et al., which considers the binary cross-entropy (BCE) loss. The same improved upper bound of $O(M^2/D)$ holds, and we transfer all the regression lower bounds by showing that on those examples the logistic path follows the least-squares path up to rescaling.

Building automation systems generate rich sensor data yet remain insight-poor because heterogeneous point naming, missing metadata, and fragmented documentation obstruct their operational use. This systematic review analyses and codes 66 peer-reviewed studies on large language models (LLMs) for HVAC operations published between 2023 and March 2026. Each study is classified across five application families and three LLM method families and assessed for evidence realism, deployment readiness, and the responsibility boundary between the LLM and physical HVAC decisions. The corpus is concentrated in building energy modelling (BEM, 32 of 66 papers), while load forecasting remains too sparse for subfield-level conclusions. Only four studies reach pilot-level evidence, and none reports sustained operational deployment. No study was classified as ready-now for industry adoption; three were near-term and 63 research-only. Nevertheless, several bounded, human-in-the-loop uses merit near-term trials, including point-name normalisation, document-grounded operator support, BEM workflow assistance, and advisory interfaces around physics-based controllers. Conventional machine learning (ML), model predictive control (MPC), reinforcement learning (RL) and ontology-based tools remain more adopted for high-frequency control, short-horizon numerical forecasting, and well-posed ontology mapping, while autonomous agentic operation and unvalidated occupant proxies remain research-stage. Current evidence therefore supports LLMs primarily as semantic and workflow layers rather than autonomous HVAC controllers. Future work should prioritise field-validated benchmarks, orchestration evaluation under operational constraints, and LLM-MPC/RL architectures with bounded latency and verifiable safety properties.

Hyperspectral and multispectral image fusion (HMIF) aims to reconstruct a high-resolution hyperspectral image (HR-HSI) by combining the fine spatial details of a high-resolution multispectral image (HR-MSI) with the rich spectral information of a low-resolution hyperspectral image (LR-HSI). Recent advances in implicit neural representations (INRs) have enabled flexible coordinate-based modeling for HMIF; however, existing INR-based approaches may not fully capture fine-grained spatial structures and rich spectral dependencies. Moreover, the LR-HSI and HR-MSI are primarily incorporated through degradation-consistency constraints, leaving their complementary information underexploited. To address these limitations, we propose Two-Stage Reconstruction with Implicit Tensor Neural Representation (TSR-ITNR), a unified self-supervised framework integrating representation refinement and observation-guided calibration. In Stage 1, TSR-ITNR learns an implicit Tucker representation and refines its low-rank spatial coefficient tensor and spectral basis to better capture fine spatial structures and interband correlations. A fixed pretrained denoiser further provides a deep prior for the preliminary reconstruction. In Stage 2, parameter-free calibration derives complementary and noninterfering corrections from both observations to recover information insufficiently captured in Stage 1. Theoretical analysis establishes the geometry-preserving property of spectral refinement and the orthogonal complementarity of calibration. Extensive experiments on multiple benchmark datasets demonstrate strong quantitative, visual, and spectral reconstruction performance without ground-truth HR-HSI supervision. Beyond conventional reconstruction metrics, we further assess the effectiveness of TSR-ITNR using downstream semantic segmentation accuracy.

Cooperative multi-agent reinforcement learning (MARL) systems rely on past experience for learning coordinated behaviour, but this experience may become unreliable if the environment or task objective changes during training. In such cases, agents first need a way to recognize that the situation has changed before deciding how to adapt. This paper studies online change-point detection for cooperative MARL using reward-derived signals. We propose \emph{Patterns of Past Rewards} (PPR), a lightweight algorithm-agnostic detector that smooths agents' return streams, highlights recent changes, and applies a statistical drift detector to flag significant shifts. We evaluate PPR in a custom Speaker-Listener environment based on the Multi-Agent Particle Environment under two controlled non-stationarity scenarios. Our results show a trade-off between detection speed and alarm stability. A smoothed-return baseline detects earlier but produces many repeated alarms. In contrast, applying the detector directly to raw returns often misses the shift. PPR offers a more balanced approach by limiting redundant detections while still identifying the controlled shifts. These findings highlight PPR as a lightweight, reward-based monitoring tool that enables cooperative MARL systems to reliably identify major changes during training.

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning capacity. We propose \textbf{RISE} (\textbf{R}ecursive \textbf{I}mprovement via \textbf{S}elf-\textbf{E}xtrapolating Policy Distillation), which constructs a synthetic teacher directly from the model's own RLVR training trajectory. By extrapolating the displacement between the current checkpoint and a trailing anchor---in parameter space or output logit space---RISE converts a sparse outcome-induced parameter update into a dense token-level target, without any external model or privileged conditioning. RISE combines RLVR and OPD in a complementary loop: outcome rewards ground the extrapolation toward correct reasoning, while the extrapolated teacher refines token-level decisions. Moreover, since the teacher is refreshed every iteration as the student improves, distillation becomes a recursive improvement mechanism rather than a one-shot compression step. Experiments spanning mathematical reasoning, multi-domain STEM, code generation, and multi-turn agentic tasks show that RISE outperforms RLVR-only training and on-policy self-distillation across all settings.

Automated reference-based evaluation methods play a critical role in assessing natural language generation systems. Existing meta-evaluation primarily measures agreement with human judgments or benchmark labels, providing limited insight into evaluator behavior under controlled conditions. We introduce behavioral correctness assumptions, a complementary framework for evaluating reference-based automatic evaluation methods. We define a taxonomy of correctness-preserving and correctness-altering assumptions and operationalize them through controlled response transformations that specify expected scoring behaviors. We evaluate diverse lexical, character-level, semantic, LLM-based, and hybrid evaluators and analyze their assumption-level behavior, stability, sensitivity, repeat-run variability, configuration sensitivity, and reproducibility. Our experiments reveal distinct behavioral trade-offs across evaluation paradigms: no evaluator satisfies all proposed correctness assumptions, and evaluators with similar aggregate performance can exhibit substantially different behavioral profiles. These findings demonstrate that behavioral correctness assumptions provide diagnostic information obscured by conventional aggregate meta-evaluation.

Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at the right time. This is challenging because visual observations alone may not disambiguate clear taking intent from accidental contact, weak grasping, wrong-direction forces, or transient interactions. In this work we treat human-robot handover as an intrinsically multimodal problem. Our approach couples a VLA model with a compliance controller that reduces interaction forces during object transfer. We finetune the VLA model with human demonstrations using RGB observation, temporally encoded tactile feedback and proprioception. We evaluate the complete system in a human-subject study against two baselines: one without tactile feedback and one using tactile feedback without compliance control. We hypothesize that combining compliance and temporal tactile encoding yields the most reliable and comfortable handovers, as compliance facilitates physical interaction while tactile history captures sustained taking intent. Performance is measured through objective metrics and an ad-hoc questionnaire. The results show that the two components provide complementary benefits and substantially outperform the baselines. Code and data will be released upon acceptance.

Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job. We test that assumption. Eight teams per setting are formed independently from one base model on the same tasks, each agent keeping a private notebook across ten formation episodes; we then trade role-matched agents between teams and measure what changes on held-out tasks. Against a placebo that reproduces the disruption of a roster change without changing who occupies the seat, a swap costs little in task score but raises the communication a team spends per unit of progress by 16 to 63 percent, and in Hanabi a swapped agent is more expensive than an inexperienced one, consistent with interference from conventions learned with its former partner. In Collab-Overcooked, when the agent that sets the agenda is replaced, most of the extra communication comes from the agent that stayed. Three ablations, over base models, decoding temperature and formation length, move the swap penalty alongside one other quantity: how far independently formed teams drift apart. Greedy decoding lowers both; doubling a team's history raises both. In these settings, agents are more fungible in task outcome than in coordination efficiency, with larger swap effects after longer formation histories.

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - particularly layer dropout - has largely disappeared from large language models (LLMs) pre-training recipes. While some prior work has reported that dropout can degrade accuracy, no comprehensive study has quantified, let alone mitigated, this effect. In this study, we show that layer dropout should be used in state-of-the-art LLM training, establishing best practices and scaling analysis for both training and post-training benefits. Concretely, with optimal layer distribution, time schedule, and optimizer hyperparameters, we observe that at the same training FLOPs layer dropout leads to lower loss. For a given number of training steps, LLMs can achieve lower or similar validation loss while saving upto 25% of training FLOPs. Moreover, layer dropout enables significant post-training optimizations, such as early exit, intermediate-layer skipping, and self-speculative decoding, yielding up to 1.5x inference speedup with negligible accuracy loss. Across more than 2400 training experiments, spanning models from 271M to 8.2B parameters and datasets up to 160B tokens, we demonstrate that these findings extend reliably to large-scale training regimes. All pre-training experiments were run on Cerebras CS-3 systems.

LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent from its output tokens alone, with no access to logits, weights, activations, or repeated sampling. Inverting speculative decoding, a small open-weight draft model scores the agent's already-generated trajectory in a single forward pass. From these speculative cross-likelihoods we extract phase-aware features by separating the reasoning and action spans, and calibrate them against a verifiable objective. SU produces a failure-likelihood score that any downstream policy, such as routing, human intervention, or extra test-time compute, can consume directly. To show the signal is actionable, we instantiate one such policy, a pre-execution veto gate, on software engineering agents Qwen3-Coder-480B and closed-source Claude 3.5 Sonnet, cutting execution error rate by 6-8 percentage points and token cost by 14-19% in deployment, transferring to out-of-distribution benchmarks without retraining, and generalizing across agent models.

Artificial intelligence (AI) is transforming not only what information systems researchers design, but also how design research is conducted. Yet existing literature offers limited guidance for computational design science (CDS) when AI actively participates in problem formulation, resource construction, design search, evaluation, and knowledge abstraction. We develop AI for Computational Design Science (AI4CDS), a five-phase methodological framework in which AI expands problem and design search while researchers retain responsibility for domain grounding, admissibility, verification, and scientific judgment. Collaboration is governed by graduated trust, reversibility, auditability, and differentiated reproducibility. We instantiate AI4CDS through ChildRiskGuard, an interpretable artifact for detecting short-form videos inappropriate for children, while documenting AI interactions, rejected alternatives, corrections, and audit trails. The case translates audience-dependent safety and explanation faithfulness into three technical challenges and develops an artifact that separates generic from child-specific risk, represents distinct developmental-risk mechanisms, and makes concept-level explanations part of the predictive computation. ChildRiskGuard achieves an F1 score of 0.769, substantially outperforming direct application of a general-purpose content-safety model while remaining competitive with strong benchmarks. The primary contribution is AI4CDS as a responsible framework for AI-enabled CDS; ChildRiskGuard provides process and artifact evidence of how AI-expanded, researcher-governed design can generate and evaluate novel computational design knowledge.

LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widened, rebound, or reinterpreted as actions cross component boundaries. We identify this failure mode as security-context discontinuity and introduce CONTINUITY, a framework for verifiable composition of agent security controls. CONTINUITY models each component with an assume-guarantee contract and carries authenticated security context across transitions using signed root grants, provenance commitments, role-bound transition receipts, bounded typed releases, transformation witnesses, and effect-bound execution permits. We formalize end-to-end consequence integrity, requiring every realized external effect to be backed by a valid and current authorization witness linking the principal, task, provenance, delegation, policy state, canonical action, and finality boundary. We implement a reference verifier and deterministic cross-layer fault-injection suite covering 32 fault classes across four application domains. In 2,560 parameterized attack instances spanning 128 fault-domain classes, the full CONTINUITY configuration commits no harmful external effect, while completing all 700 benign tasks and escalating all 200 ambiguous cases. These results show that secure agent execution requires not only sound individual controls, but explicit contracts that preserve their guarantees across the complete instruction-to-effect path.

World-action models guide action generation with predicted future observations, but vision-centric predictions miss the local contact cues that decide contact-rich manipulation. However, naively predicting future tactile observations as additional views recovers only a third of the achievable gain in our experiments. This gap reflects a timing mismatch: predictions precede execution, while tactile feedback arrives during it. We introduce TacPAC, which turns tactile prediction into real-time action correction. Once the base model has planned an action chunk, TacPAC caches the predicted contact that plan was conditioned on together with the plan's own representation, and a tactile expert reads each newly observed tactile image against that cache to correct the actions not yet executed. Feedback is thus interpreted against what the plan anticipated rather than in isolation, and one correction is a single pass over that cache, $20.7\times$ cheaper than regenerating the chunk. On five real-robot tasks spanning precision insertion, fragile-object handling, object reorientation, and long-horizon manipulation, TacPAC leads every task and raises the average from 22% for its vision-only base model to 64%. Code is available at https://github.com/LogosRoboticsGroup/TacPAC.

Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval and flat skill summarization, fundamentally ignoring the temporal dependencies and outcome-conditioned topology of agent behavior. We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy. Trace2Tower abstracts step-level interactions into canonical events, constructing a unified graph governed by semantic compatibility, transition dynamics, and outcome evidence. Through a novel contrastive spectral decomposition, it isolates stable, success-aligned behavioral modes while rigorously suppressing failure-prone shortcuts. These modes organically populate a dynamic skill tower of action templates, procedural routines, and overarching task strategies, continuously refined via verifier-guided feedback. On ALFWorld, Trace2Tower achieves 87.31% success requiring only 10.35 steps and 0.26 invalid actions; on WebShop, it reaches 50.67% exact success. Across both benchmarks, Trace2Tower significantly outperforms existing baselines in task mastery and context-efficient experience reuse.

Natural-language instruction changes can directly alter robot behavior. A reliable embodied system should preserve its action when the task is unchanged and update it correctly when the task itself changes. We introduce One Word, Different Action, a real-robot benchmark built on physical decision states and executable actions, using task-preserving and task-changing instruction pairs to jointly evaluate Decision Invariance and Decision Sensitivity, with further evaluation under multi-constraint reasoning and real-RGB grounding. Experiments show that modern models are near saturation on single-constraint instruction changes, yet several models degrade noticeably when multiple task constraints must be integrated into one executable decision. These results suggest that the more salient remaining challenge is no longer recognizing an isolated instruction change, but reliably composing multiple task requirements into a correct robot action decision.

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or business rules can change the resulting mathematical program. Existing evaluations largely assume a complete specification and therefore overlook whether an agent knows when clarification is needed before modeling. We introduce OR-Clarify, a benchmark for pre-formulation clarification. Each task presents a partial public problem description, withholds structured hidden slots, and evaluates agents through bounded interaction with a simulated user. The benchmark supports both openended and choice-based clarification, and measures slot recovery, stopping behavior, silent assumptions, and interaction cost. We further propose Interactive Optimization (InterOPT), a two-stage framework that identifies unresolved formulation-critical gaps and uses them to guide whether to ask the next question or to stop. In our choice-based experiments, InterOPT substantially outperforms all baselines in exact slot recovery; in the open-ended setting, it remains competitive with strong prior methods. Together, OR-Clarify and InterOPT reframe OR assistance as a selective completeness decision: clarify when needed, stop when ready, and quantify what remains missing.

Commonsense reasoning in computer vision encompasses integrating visual data and contextual knowledge, crucial for enhancing AI's understanding of everyday scenarios. This understanding not only improves machine learning models but also enhances their ability to interact meaningfully with humans and the environment. Unlike CNN-based conventional vision models, which are designed to identify objects within a specific image, incorporating commonsense knowledge enables models to interpret scenes in a more holistic manner, thereby improving their spatial ability to reason about relationships among objects and actions. This integration not only enhances object recognition but also facilitates a deeper understanding of the contextual factors, ultimately leading to more precise predictions and interactions in real-world applications. This paper presents a comprehensive survey of recent developments that integrate commonsense knowledge into computer vision tasks. We systematically review approaches based on knowledge graphs, scene graphs, neuro-symbolic models, and commonsense-augmented transformers. We also outline current limitations related to dataset bias, knowledge incompleteness, and integration challenges. Finally, we highlight prospective research trajectories in cross-modal reasoning, scalable commonsense knowledge injection, and neuro-symbolic hybrid architectures to develop truly intelligent visual systems.

Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH). Although efficient to evaluate, SH coefficients dominate per-primitive storage and memory traffic, while their band-limited basis restricts angular detail. We present a thorough, end-to-end comparison of SH and recent spherical appearance models and introduce an implicit alternative that decodes compact per-primitive latent codes using a tiny shared MLP. We integrate all models into the same optimized pipeline, fusing their forward and backward passes into a differentiable CUDA rasterizer and provide a portable WebGL viewer for laptop and mobile GPUs. Our evaluation across reconstruction quality, memory use, and optimization and rendering performance shows that recent spherical models offer the strongest overall quality-efficiency trade-off. Our neural representation is the most compact model evaluated and, compared to third-degree SH, reduces the per-primitive appearance footprint from 192 to 28 bytes, accelerates optimization by 1.3$\times$, while improving reconstruction quality. We further analyze how appearance parametrization shapes optimization, identifying differences in recovered geometry and the tendency of expressive models to absorb non-static scene content. Together, our framework and analysis provide practical guidance for replacing SH beyond what image metrics alone can capture.

We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph Descriptor Prompt (GraphDP), creating a text bridge that enables domain-agnostic anomaly scoring. By enforcing multi-scale consistency through Matryoshka representation slices, the model captures anomalous deviations at multiple levels of granularity. For scoring, we formulate anomaly detection as density estimation on the aligned hypersphere and introduce Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density estimators in both graph and text embedding spaces. This probabilistic formulation recovers angular k-nearest-neighbor scoring as a high-concentration limiting case and provides a principled fusion of structural and semantic anomaly signals. The shared text embedding space further serves as a cross-domain bridge: by encoding a target domain's GraphDP without target-domain training data, GLASS performs zero-shot anomaly detection, and with only a handful of normal examples, few-shot adaptation via reference-set calibration. Across twelve benchmarks and three meta-domains, GLASS obtains the best average AUROC and rank compared with recent advanced GLAD baselines and enables effective cross-domain transfer.

As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely restricts the development of verifiable radiation mitigation strategies. Open-source, register-transfer level (RTL)-accessible accelerators resolve this limitation by enabling user-defined instrumentation, yet few have empirical radiation-response baselines. This work establishes a foundational system-level proton-irradiation baseline for an unmitigated open-source Tensil NN accelerator deployed on a Zynq UltraScale+ SoC executing ResNet-20 inference. Under 20 to 58 MeV proton irradiation, we delivered $4.29 \times 10^{10}$ p/cm$^{2}$ within monitored operational windows. Seven workload interruptions required two restarts of the notebook process, four reboots or board resets, and one power-cycle sequence. Two output-corruption events returned incorrect CIFAR-10 classes without loss of service. In the longer event, the accelerator returned a class absent from the ten-image CIFAR-10 pool for 39 consecutive inputs at normal cadence. The process remained alive, while the kernel log, limited memory test, and sampled power showed no anomaly. Observation of the stuck-class sequence ended with scheduled bitstream reconfiguration. All nine onsets occurred under the nominal 4 cm beam, which exposed the SoC, LPDDR4, and additional board circuitry; none occurred under the 2 cm SoC-centered field. This pattern shows a field association but does not establish LPDDR4 as the cause because field size was confounded with run order and dose. Linux-managed accelerators require end-to-end content checks and recovery that reaches the state in which corruption can persist. This baseline documents availability loss and silent output corruption, supporting future software hardening of COTS FPGA-SoCs for neural-network inference in space systems.

Human knowledge is inherently structured and interdependent: mastery of a concept requires prior mastery of its prerequisites, a principle formalized by Knowledge Space Theory (KST). While LLMs achieve strong performance on complex reasoning tasks, it remains unclear whether they exhibit coherent, human-like knowledge structure. We introduce a KST-grounded framework for evaluating LLM knowledge structure in mathematical reasoning, using it as a normative framework to analyze whether LLM behavior adheres to principled knowledge dependencies. Evaluating eight open- and closed-source LLMs against real human learners, we find that (1) LLMs do not adhere to human knowledge structure -- they frequently violate knowledge dependencies and fail to leverage related knowledge provided in context to improve performance on dependent questions; (2) LLMs do not share a consistent knowledge structure among themselves, as reflected by low overlap in their knowledge distributions. Furthermore, these structural deficiencies remain largely invisible to accuracy-based and LLM-as-judge evaluations. Together, our results provide behavioral evidence that current LLMs knowledge does not follow a human-like structure.

We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a detect-to-track pipeline to a new target domain without access to target-domain labels. Rather than optimizing against annotated metrics, the VLM directly inspects rendered tracking outputs, identifies visual failure modes, and recommends parameter updates through an iterative tuning loop. We first demonstrate that ground-truth-supervised hyperparameter transfer can be brittle. On MOT17->MOT20, applying a source-derived oracle configuration reduces mean HOTA by 0.090, from a target-domain ceiling of 0.357, to 0.267. Without using any target-domain labels, our VLM-based tuner recovers 67.8% of this lost headroom, finishing within 0.029 HOTA of the target ceiling; on the highest-density target sequence, it recovers up to 86.7%. We further show that label-free Bayesian optimization with handcrafted proxy objectives struggles under large domain shifts and can degrade configurations that are already strong. In contrast, the VLM tuner acts selectively: when its visual diagnosis reveals no clear failure mode, it declines to modify the configuration, preserving performance on easy transfers while improving hard ones. Finally, we characterize the conditions under which this approach succeeds, namely, when domain shift manifests through exposed detection-level parameters, versus where it is less effective, such as MOT17->DanceTrack, where the source oracle is already near-optimal.

While machine-learning interatomic potentials (MLIPs) have successfully learned potential energy surfaces (PES) and atomic forces, many practical applications, such as vibrational analysis and transition state search, rely heavily on the PES Hessian. Yet, standard MLIPs tend to be trained on energy and forces alone, leaving Hessian information largely unexploited. Meanwhile, existing methods that explicitly incorporate the Hessian into training objectives require architectural modifications and introduce significant computational and memory overheads due to higher-order backpropagation. To address these limitations, we propose two Hessian-derived data augmentation schemes: isotropic Gaussian displacement (\textbf{UniAug}) and normal mode-weighted displacement (\textbf{ModeAug}). Both methods utilize simple Taylor expansions, achieving effective augmentation without altering training objectives or extending the autograd graph. This allows seamless, plug-and-play integration with existing architectures and training pipelines. Comprehensive evaluations across non-equilibrium and equilibrium datasets demonstrate that our approach enhances model accuracy while providing practical, task-specific guidelines.

Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine what counts as a suitable plan. We call the absence of this execution context from an agent's planning state substrate blindness. We test this general proposition through numerical code generation, where selected implementation choices and operational consequences are directly observable. Three frontier model configurations--Anthropic Claude Opus 5, OpenAI GPT-5.6-Sol, and Google Gemini 3.7 Flash--generate code for a high-dimensional pairwise Euclidean-distance task either from the task alone or with a 128 MB RAM and 10.0 s wall-time contract. Contract disclosure reduced measured peak process memory in 13 of 14 executable index-aligned task-only versus contract-disclosed comparisons and reduced mean wall time in all three cohorts, making execution up to 3.1x faster. Across the audited corpus, disclosure produced structural code changes including bounded blocking, float32 retention, upper-triangle traversal, and in-place or memory-mapped buffers. At a tighter 96 MB contract, independently sampled contract-disclosed cohorts achieved correct-and-within-budget outcomes of 4/5 for Claude Opus 5, 5/5 for GPT-5.6-Sol, and 3/5 for Gemini 3.7 Flash, compared with task-only outcomes of 0/5, 1/5, and 0/5; cohort mean MaxRSS and wall time were 49-74% and 35-64% lower than their task-only references. These results establish a controlled proof of concept for substrate-aware agent planning: a minimal execution contract induces proactive structural adaptation in generated programs, shifting computation away from unconstrained allocations and substantially improving observed resource-time profiles before execution.

Mixture-of-Experts (MoE) architectures provide an efficient paradigm for scaling large language models (LLMs), yet fixed top-k routing activates the same number of expert slots for every token, causing substantial redundant computation. Existing expert-skipping methods often rely on router confidence, calibration data, or additional training, and therefore cannot reliably estimate the actual contribution of routed experts. To this end, we propose ACE, a training-free, calibration-free, and checkpoint-preserving framework for token-adaptive expert skipping in MoE-based LLMs. ACE contains two complementary components: 1) Global Spectral Proxy (GSP), which estimates global transformation capacity from the coupled gate, up, and down projections together with RMSNorm scaling; and 2) Router-Conditioned Refinement (RCR), which constructs expert-specific direction prototypes from centered router weights and evaluates expert responses along routing-preferred directions. During inference, ACE combines both estimates with runtime router gates and skips an expert slot only when both views identify it as low-contribution, while always retaining the top-1 expert. All expert statistics are computed offline, leaving only table lookups and lightweight scalar operations online. Extensive experiments across three MoE-based LLMs and eight benchmarks demonstrate that ACE consistently outperforms existing static and dynamic baselines, with increasingly pronounced advantages under aggressive expert skipping. For instance, at a 50% skipping ratio on Qwen3.6-35B-A3B, ACE reduces WikiText-2 perplexity by 7.96% and improves average downstream accuracy by 4.15 percentage points over the strongest competing method.

Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewer assignment, and review manipulation as separate stages, leaving the lifecycle effects of collusive bidding unclear. Real-world analysis is further constrained by typically unobservable collusive intent and the lack of counterfactuals for the same conference. Motivated by this gap, we introduce \alg, an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies. We further develop an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affinities to construct collusion rings and select target papers, producing expertise-consistent rather than arbitrarily targeted attacks. Controlled experiments show that collusive bidding more than doubles target-paper capture and that assigned colluders score target papers about two points higher than honest co-reviewers, while conference-wide effects remain comparatively modest. Evaluated bid-phase detectors provide only limited evidence of collusion: in a fixed-triplet detector stress test, native positive-bid graphs are confounded by benign affinity, while a Very-High-only diagnostic view enables precise but low-coverage local recovery.

Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in their potential to act as autonomous agents for real-world tasks. However, scenarios requiring agents to fulfill users' complex, structured requirements remain largely underexplored. In this work, we examine reasoning tasks under three distinct requirement scenarios: (i) Must-have requirements uniquely determine a unique feasible solution; (ii) Multiple answers satisfy the must-have requirements and are prioritized via the nice-to-have requirements; and (iii) No candidate solution satisfies the must-have requirements, in which case the agent should abstain from generating a response. We evaluate state-of-the-art MLLMs on 3,649 carefully constructed problems that reflect realistic service scenarios, including e-commerce, booking, and map-based or ride-hailing. Our evaluation reveals that existing MLLMs exhibit catastrophic failures in all scenarios. They frequently misinterpret task requirements, violate must-have requirements, and produce invalid solutions. To address this critical gap, we propose First Things First Reinforcement Learning FTF-rl that explicitly optimizes reasoning over multi-priority user requirements. Experimental results show that our method substantially improves the task success rate compared to strong baselines. Moreover, FTF-rl yields general effectiveness on popular logical and mathematical reasoning tasks, including LogicVista, MathVision, and InfoQA. Our findings suggest that enhancing requirement-aware reasoning capability provides a simple yet effective pathway to improve generalization of MLLM agents. Code and dataset are available at https://github.com/claire62/FTF-RL.

Robotic hands vary widely in anatomical fidelity and mechanical complexity, and these structural choices influence the coordination of joint motions and the difficulty of controlling the system. A unified framework is presented in which the kinematic and actuation stages are analysed separately and in composition, through the conditioning of the task Jacobian, the actuation matrix, and their product. It is applied to two hands representing opposing design philosophies, the Shadow Dexterous Hand and the Anatomically Correct, Biomechatronic Hand, along four morphological aspects: joint axis geometry, actuator-to-DOF ratio, coupling architecture, and authority distribution. All parameters are derived from the hands' canonical digital representations. Anatomical fidelity carries no uniform advantage: oblique axes improve thumb conditioning but leave the long fingers worse conditioned than the orthogonal-axis design, while the branching tendon network improves the effective control mapping at every long finger and worsens it significantly at the thumb, where actuator authority is concentrated on thumb opposition. Predictions derived from these metrics are evaluated against reinforcement learning experiments using PPO, DDPG+HER, and TQC+HER, across three different tasks.

Multi-modal learning has demonstrated strong potential in medical applications by integrating heterogeneous data sources such as medical imaging, clinical records, and genomics to improve predictive performance and support clinical decision-making. However, advances in this area are often constrained by two key challenges: the limited availability of well-curated, ready-to-use datasets that accurately reflect real-world conditions, where medical data are frequently collected inconsistently and are often incomplete; and the inherent difficulty of integrating heterogeneous data modalities. In this work, we introduce a newly curated multi-center, multi-modal, and longitudinal dataset designed to support the evaluation of a wide range of learning pipelines under realistic conditions. The dataset comprises a total of 1,365 lung cancer patients and has three imaging modalities (whole-slide images, CT scans, and PET scans), structured clinical data, transcriptomic, and longitudinal follow-up and treatment information. For each imaging modality the dataset contains more than one instance. Moreover, the dataset exhibits substantial and non-uniform missingness across modalities, making it well-suited for studying robust multi-modal fusion strategies. We further provide both uni-modal and multi-modal benchmarks on the task of 12-month overall survival prediction, disease-specific survival, as well as longitudinal benchmark of hazard prediction under severe missing data. Our results show that, despite high levels of missingness, integrating complementary modalities consistently improves predictive performance over uni-modal approaches, highlighting the value of multi-modal fusion in realistic clinical settings. The dataset and benchmark code are available at https://github.com/ritacmendes/MMIST-LUNG.

We consider safety-critical control problems involving multiple requirements with different priorities and uncertainty in their evaluation. We represent these requirements using risk-aware rulebooks, where each requirement is assigned a risk measure and an acceptable threshold, and a priority relation is defined among the requirements. Each requirement induces a risk-evaluation function that maps a policy to the risk associated with its violation. We formulate risk-aware optimal control with rulebooks as a lexicographic optimization problem over excess risks and develop an anytime filtering and branch-and-bound algorithm that progressively tightens the certified optimality gap while characterizing the corresponding set of policies at each priority level. The algorithm returns a policy together with these gaps, which bound its suboptimality. We prove that these gaps are valid for any finite computational budget and, under additional assumptions, converge to zero as the computational budget increases. We evaluate the algorithm on a synthetic benchmark with a known optimum and a realistic highway-merging simulation with CVaR-based collision, rear-braking, headway, and comfort rules.

On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric mechanisms in OPD remain relatively underexplored. This paper presents a empirical study of data efficiency and data selection in OPD. We begin by investigating an extreme setting: training OPD on only one example, namely 1-shot OPD. Surprisingly, we find that 1-shot OPD is consistently effective across all sampled training examples and harder examples often yield superior performance gain. We next investigate what actually drives the student model's improvement in the training data. Our analysis reveals that the improvement is not driven by high token entropy, but the longer CoT paths which hard problems naturally generate. Training on longer CoT can help maintain closer alignment with the teacher over a long reasoning horizon, and learn critical thinking patterns usually missing in short CoTs, such as reflection (e.g., ``Alternatively''). Based on these insights, we propose a simple data selection method that selects only hard examples for training, where even ``unsolvable'' examples that completely exceed the teacher's capability can be successfully used. Our experiments conducted on four models ranging from 1.5B to 7B show that training the student model on only 8 selected hard examples matches the performance of the 17K dataset baseline.

The number of discrete class-separability jumps observed during ResNet finetuning is examined empirically as a predictor of final test accuracy. Across 75 experiments spanning four benchmarks (CIFAR-10, CIFAR-100, TinyImageNet, and CIFAR-10-C) and three architectures (ResNet-18, ResNet-50, and ResNet-101), with five to ten seeds per configuration, a strong within-dataset negative correlation is obtained on standard i.i.d. classification benchmarks: \(r = -0.84\) on CIFAR-10 (\(p < 10^{-8}\), \(n = 30\)) and \(r = -0.87\) on CIFAR-100 (\(p < 10^{-5}\), \(n = 15\)). Under distributional stress, the relationship attenuates: TinyImageNet yields \(r = -0.45\), and the CIFAR-10-C corruption benchmark yields \(r = -0.19\). Two additional analyses discipline the empirical claim. A partial correlation controlling for architecture depth, treated as a linear covariate, shows that on CIFAR-100 the transition count retains statistically significant predictive power (\(r_{\mathrm{partial}} = -0.69\), \(p = 0.007\)); the corresponding result under the stricter categorical conditioning is not established at \(n = 15\). A comparison against six alternative training-curve signals shows that transition count achieved the strongest correlation among the evaluated signals on CIFAR-100 and one of the strongest on CIFAR-10, but is dominated by other signals on the two stressed benchmarks. The comparison is restricted to training-curve-level signals; comparisons against effective rank, Hessian sharpness, Fisher information, margin, and neural-collapse measures, which are the strongest competitors in the current literature, are not part of the present study and remain open. The observation is presented as an in-distribution training-quality probe among a family of candidate probes, and an inexpensive detection procedure suitable for logging alongside a standard training loop is provided.

In this paper we illustrate a novel architecture generating interpretable behavior and explanations. We refer to this architecture as the Mirror Agent Model because it defines the observer model, that is the target of explicit and implicit communications, as a mirror of the agent's. With the goal of providing a general understanding of this work, we firstly show prior relevant results addressing the informative communication of agents intentions and the production of legible behavior. In the second part of the paper we furnish the architecture with novel capabilities for explanations through off-the-shelf saliency methods, followed by preliminary qualitative results.

Vision-Language-Action (VLA) or World Action (WAM) models have recently demonstrated remarkable performance in robotic manipulation. On LIBERO, SOTA method have achieved nearly 100\% success rates, seemingly suggesting that the models are ready for deployment in real world. However, near perfect performance on existing benchmarks can be misleading: success under ideal conditions does not imply real world robustness. Existing benchmarks primarily evaluate task completion from predefined initial states, while real world interactions inevitably involve failures such as failed grasps, collisions, and unintended object movements. A robot must therefore not only execute tasks successfully, but also recognize and recover from failures to continue the task. Yet this capability remains largely unmeasured, revealing a critical gap between benchmark performance and real world reliability. To address this gap, we introduce LIBERO-Recover Benchmark, a large scale benchmark for failure recovery in robotic manipulation. Built upon LIBERO, we collect real execution failures from SOTA embodied models and construct 1,000+ scenarios across four recovery levels: (1) Action Retry, (2) Action Adaptation, (3) Object State Recovery, and (4) Environmental Recovery. We evaluate four core capabilities: spatial understanding, object structure reasoning, interaction understanding, and topological reasoning. As the first large-scale benchmark for embodied failure recovery, LIBERO-Recover shifts evaluation from \emph{Can the robot succeed?''} to \emph{Can the robot recover after failure?''}, promoting robust and generalizable embodied agents. The project will be avaible in \textcolor{blue}{https://liulin815.github.io/LIBERO-Recovery/}.

Image generation and editing models have advanced rapidly, yet remain unreliable when prompts require external world knowledge. Bounded and long-tail parametric knowledge prevents direct or reason-then-generate approaches from recovering the required facts and visual appearances. Existing agentic generation and editing methods mitigate this limitation with retrieval tools, yet remain constrained by insufficient visual verification, overloaded policy models, and weak integration of retrieved textual and visual evidence. To address these limitations, we present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend. We first introduce WeAgent-Harness, a multimodal runtime with persistent evidence management and dedicated verification and integration tools that organize retrieved multimodal evidence into a dense carrier. Upon this, we develop a scalable pipeline for prompt synthesis and agentic trajectory collection, yielding 23K supervised trajectories and 14.7K RL tasks with three-layer verifiable checklists. We further introduce WeBench-MMGenEdit, a bilingual benchmark covering both knowledge-intensive image generation and multi-image editing. Finally, a two-sided post-training recipe based on SFT and RL improves the agent policy and image backend. Together, WeAgent-MMGenEdit enables a 30B-total/3B-active policy to outperform similarly sized policy models and approach the performance of a 1T-parameter agent.

Formalizing mathematics in a proof assistant, where a machine checks every definition, statement and proof, has set a new standard of rigor. Large language models are now capable of formalizing autonomously, even at the scale of whole textbooks. We bring this standard of rigor to physics, where theoretical arguments carry idealizations that are rarely stated fully, and any logical gaps could have a cascading effect on interdependent results. Recognizing the need to evaluate autoformalization systems for physics, we release AxQM, 1,019 kernel-checkable proof-synthesis tasks over 479 items drawn from the textbook Quantum Computation and Quantum Information by Nielsen and Chuang. The tasks are stated in a custom Lean library of finite-dimensional quantum mechanics. By task count, it is the largest proof-synthesis benchmark in physics by a factor of four. AxQM is derived from a near-complete formalization of the formal portions of the textbook, so every task is guaranteed a solution, which we keep private. Grading of the benchmark is done deterministically by the Lean kernel, which checks that the proof compiles, that no sorry appears in it or in any declaration it depends on, and that it introduces no new axioms.

Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their performance relative to the original model. To address this limitation, we propose DEX-Comp, a two-stage training recipe: Pure Distillation warm-starts the compression model on the uncompressed RAG's correct responses only, and Hard Exploration then runs reinforcement learning solely on queries the uncompressed RAG fails, forcing the model to explore computation patterns better suited to compressed representations. On five open-domain QA benchmarks at retrieval depths from top-5 to top-30, DEX-Comp compresses retrieved contexts by $16\times$ and accelerates inference by $4\times$--$24\times$, while achieving performance comparable to or exceeding the uncompressed RAG baseline across retrieval depths. Ablations and evaluations across diverse datasets and backbones further confirm the contribution of each stage and the generalization of our approach.

The integration of artificial intelligence (AI), particularly large language models (LLMs), into educational assessment has opened new opportunities to enhance the efficiency and scalability of grading processes. This study presents the design and validation of an AI-assisted scoring framework for written responses in a large-scale national assessment. The proposed approach focuses on short written texts of approximately 150-200 words and incorporates a human-in-the-loop strategy to preserve assessment quality while reducing manual workload. The study is grounded in a real operational context, using data from two recent editions of a nationwide test, each comprising approximately 5,000 student responses. We analyze the alignment between AI-generated scores and human raters across multiple rubric dimensions, as well as the impact of the proposed decision flow on pass/fail outcomes. Results show moderate to high agreement between the model and human evaluations in most dimensions, supporting the feasibility of AI assistance in this setting. Moreover, the proposed correction workflow identifies cases where human review is most valuable, enabling a more efficient allocation of expert effort. The findings suggest that AI-assisted scoring can be safely integrated into large-scale assessment processes only when combined with carefully designed human oversight. The paper concludes by discussing practical implications for deployment in national assessment systems and outlining future research directions, including longitudinal monitoring of model-human alignment and the analysis of potential cognitive bias introduced by AI-supported review workflows.

Scientific papers require models to reason jointly over text, equations, figures, tables, code, and datasets while preserving the provenance of supporting evidence. Existing benchmarks typically evaluate these capabilities in isolation, leaving unclear whether multimodal models can support realistic scientific-reading workflows. We introduce SciDocBench, a workflow-centered benchmark for scientific document understanding. It contains 124 expert-authored and difficulty-screened questions organized into seven research-assistant capability groups and 19 subtasks across five scientific domains. Each question is instantiated under four matched conditions combining English or Chinese questions with all-images-first or interleaved document representations, yielding 496 evaluation instances for controlled analysis. The strongest evaluated system achieves only 62.6/100, with pronounced weaknesses in document perception, evidence grounding, verification, and cross-document reasoning. To translate these diagnostics into scalable training signals, we introduce SciDocIR, a typed evidence-graph representation that preserves scientific document objects, layout and cross-reference relations, and provenance. Building on SciDocIR, we construct SciDocDataset, comprising approximately 15K supervised fine-tuning samples and 8K reinforcement-learning samples across 14 verifiable subtasks. Together, SciDocBench, SciDocIR, and SciDocDataset form an evaluation-to-training framework for diagnosing and improving scientific-document assistants. The project page is available at https://github.com/InternLM/SciDocBench.

Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed across chapters, relations evolve over narrative time, and correct answers may depend jointly on temporal, spatial, and relational constraints. We propose NS-ST-GraphRAG, a neuro-symbolic spatio-temporal GraphRAG framework that integrates ontology-guided extraction, deterministic constraint checking, dual temporal coordinates, spatial scene attributes, and dynamic sub-graph retrieval. Instead of retrieving from a single corpus-level graph, the framework selects the graph state valid for the temporal and spatial scope of a query and grounds generated answers in traceable evidence. We further introduce Red-Chamber-QA, to our knowledge the first open multi-hop question-answering benchmark for classical Chinese literature, with time-, space-, and general-question categories, per-part evidence spans, and deterministic shortcut controls. On a 120-question held-out split, NS-ST-GraphRAG achieves mechanical answer reproduction of 0.733 versus 0.675 for the frozen window baseline and 0.083 for a closed-book model (McNemar exact p = 0.092, directionally favorable but not significant); semantic-judge accuracy is 0.866 versus 0.850. The pre-specified constrained-category condition of H2 is not supported by the delivered comparison. These results show how temporal graph representation, constrained extraction, and auditable evaluation integrate into a unified framework for verifiable knowledge processing over long-form narrative.

Automatic identification of code-switched (CS) utterances remains a challenge for language identification (LID) systems, causing such texts to be underrepresented in the training data of Large Language Models. In this paper, we revisit MaskLID, a state-of-the art approach for CS identification, which requires no training and detects arbitrary language combinations. We make three main contributions: (a) we reveal, and address, a major issue of MaskLID: its overreliance on word-level language association scores; (b) we reformulate the underlying optimization algorithm as an Integer Linear Program, enabling us to experiment with a large set of clear and interpretable constraints; (c) each of these improvements vastly improves the baseline system, as we illustrate in experiments involving 10~diverse languages, where we observe a strong boost in performance on CS benchmarks. We release our code and data for reproducibility.

Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We introduce TIER, a Threat Implicitness Benchmark for behavioral safety evaluation of LLMs. TIER covers four risk domains and four threat levels, from explicit harmful requests to sophisticated jailbreaks. Responses are assessed using a six-label behavior scale and two independent LLM judges. Experiments on six open-weight LLMs show that safety behaviors evolve gradually across threat levels rather than shifting directly from refusal to compliance. Contextual prompts yield the most diverse behaviors, while jailbreaks reveal the largest robustness gaps. Furthermore, models with similar Attack Success Rates can exhibit distinct response distributions, highlighting the need for behavior-aware LLM safety evaluation.

Biological agents navigate familiar environments not by re-solving routes for each new goal, but by reusing a learned map built once and read off as goals change. Existing artificial cognitive-map models mimic this reuse, yet their guidance is not explicitly grounded in additive heterogeneous route costs. Furthermore, they often struggle with memory efficiency: representative state-indexed and high-rank spectral constructions incur substantial storage growth as the environment scales. We present BCM, which grounds a reusable cognitive map in local edge costs through a self-supervised Bellman-grounded objective and a compact coordinate encoding, supporting changing goal queries without per-goal retraining. On weighted grids of up to $N=1600$ nodes, BCM maintains full success and only a 5\% mean Gap relative to exact Dijkstra search, compared with about $45\%$ for a connectivity-based spectral baseline. Notably, as the graph size increases from $N=400$ to $N=3600$, its memory footprint grows sublinearly while maintaining competitive performance, making our method scalable to complex environments. Together, these results show that additive route costs can be written into a compact, reusable cognitive-map representation, bridging the gap between biological flexibility and optimal path planning.

AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discovery by generating novel ligands directly within target protein binding pockets. We present NEAT-POCKET, a pocket-conditioned extension of the autoregressive NEAT model for 3D molecular generation. NEAT-POCKET generates molecules atom by atom in protein pocket environments while preserving atom permutation invariance and explicitly modeling hydrogen atoms. Benchmarks on the CrossDocked and SPINDR datasets show that NEAT-POCKET achieves competitive structure-based generation performance while sampling substantially faster than existing baselines. Beyond full-molecule generation, NEAT-POCKET naturally enables pocket-conditioned fragment completion, a task directly relevant to lead optimization and scaffold elaboration. These results position NEAT-POCKET as a fast, flexible, and practical framework for structure-based drug design.

We present Discovery Loop, a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms. Starting from a simple seed solver, the LLM proposes algorithmic improvements guided by a scoreboard of results and a history of prior ideas. Each candidate is evaluated against an independent verifier; improvements are kept and failures discarded. Applied to the Packomania circle-packing benchmark (csqv: maximize the sum of radii of N variable-radius circles in the unit square), the system improved the best known solutions for 10 values of N in the range 101-114, with gains of 2.4%-5.4% over prior records, all within 15 iterations and at a total LLM cost of $27.72. These results have been independently accepted by Packomania. We describe the method, analyze cost-efficiency dynamics including an adaptive plateau-detection mechanism, and discuss implications for democratizing automated scientific discovery.

Evaluation of medical artificial intelligence agents remains predominantly answer-centric, assessing only the correctness of final outputs while overlooking the quality of intermediate reasoning. In clinical settings, however, a correct answer reached through fabricated evidence or incoherent logic is as dangerous as an incorrect one. We propose MedTraj, a framework that treats reasoning trajectories as critical objects for construction, evaluation, and optimization. The pipeline generates structured multi-step reasoning chains from medical reasoning sources. Each trajectory is then parsed into clinical observations, evidence, numbered reasoning steps, and a final conclusion, and scored across five quality dimensions: coherence, evidence support, hallucination, completeness, and traceability. Controlled error injection introduces targeted faults into otherwise correct trajectories to establish causal links between specific reasoning failures and measurable quality degradation. Building on this, step-level filtering based on marginal contribution identifies which individual reasoning steps drive or undermine trajectory quality. Finally, quality-weighted context learning feeds trajectory evaluations back into the model at inference time, allowing it to learn from both strong and weak reasoning demonstrations. Experiments across CareQA, PubMedQA, and CECMed demonstrate that trajectory context consistently improves reasoning coherence, with gains of +0.029 to +0.041 over a zero-shot baseline. On CECMed, quality-weighted context nearly doubles the correctness over the zero-shot baseline while cutting the hallucination ratio by 87%. Marginal-contribution analysis further shows that a small minority of reasoning steps carry most of the quality signal, and that extending chains beyond four steps yields diminishing returns.

Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses and write research reports, but executing a prescribed analysis is not the same as making a discovery. Existing benchmarks are configured for reproduction: tasks, data, and rubrics are built around a hidden target study, and recovery of its result is rewarded. We present TruthInsightBench, a benchmark configured for discovery. Its 40 blind tasks, drawn from 40 peer-reviewed studies across 10 scientific domains, expose only a neutral scientific objective and frozen data; source conclusions, expected values, and analysis paths are withheld, leaving the agent to determine what claim the data support. A fixed LLM-based judge scores the evidentiary maturity of an agent's own claims along six dimensions, operationalized as 29 artifact-grounded items, with automated, deterministic aggregation and no per-instance human grading, so evaluation can be repeated automatically as agents evolve. On one frozen base model, four coding agents form a narrow plateau (58.4-60.3 of 100) with no statistically reliable pairwise separation: they execute and document analyses competently, with comparatively strong evidence auditability and novelty, but largely lack the discriminating acts that establish a trustworthy claim (controls, robustness, falsifiability, and cross-dataset generalization). The bottleneck is scientific judgment rather than coding, and genuine discovery remains out of reach. TruthInsightBench makes this gap a measurable target; data and scoring code are at https://github.com/TruthInsight-stack/TruthInsightBench.

General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic yet challenging setting for continual intelligence. Although pretrained models (PTMs) provide rich prior knowledge for addressing the limited supervision and non-stationary nature of GCL, existing PTM-based methods often directly adapt pretrained representations and overlook two critical gaps: the misalignment between upstream pretraining and downstream continual adaptation, and the unreliability of conventional output alignment under blurry streams. Here we propose MePo++, a unified post-training framework that bridges pretrained knowledge and downstream GCL through representation refinement and reconciliation. MePo++ introduces two complementary components: MetaPrep, which improves representation plasticity for continual adaptation through unsupervised meta-refinement over pseudo continual sequences; and StreamAlign, which reinforces representation stability by reconciling evolving online features with a stable pretrained geometry. By improving representation learnability before adaptation and preserving alignment during continual learning, MePo++ enables PTMs to remain both plastic for new concepts and stable over evolving streams. Experiments across diverse PTMs, datasets, and continual learning baselines demonstrate the consistent effectiveness and generality of MePo++ for PTM-based GCL. Our code is available at https://github.com/SunGL001/MePo_Plus.

Automated gastrointestinal (GI) endoscopy classification requires models that generalize across diverse modalities and class distributions, often far from natural-image pretraining. We propose MultiAttenGastro, a plug-and-play attention framework with parallel 1-D channel, 2-D spatial, and 3-D contextual heads, and present the first systematic cross-dataset evaluation across eight CNN and transformer backbones on five public GI datasets (80 backbone--dataset runs). We find that attention effectiveness is not universal but tracks the representational gap between ImageNet features and the target distribution: MultiAttenGastro improves 6 of 8 backbones on Kvasir-Capsule (14-class WCE, large gap; best macro F1 98.33\%), is uniformly negative on the small-gap Kvasir-v2 benchmark (0/8), and shows mixed outcomes on datasets with intermediate gap. Five-seed ablation on the strongest case (Kvasir-Capsule, ConvNeXt-Tiny) shows this improvement is directionally consistent, but not statistically decisive (paired $t$: $p=0.47$; Wilcoxon: $p=0.63$), and that individual attention heads are not uniformly beneficial in isolation only their combination yields a positive mean effect. Centered Kernel Alignment (CKA) analysis links this pattern to representational redundancy: low inter-head CKA under large domain gaps coincides with the framework's only consistent gains, while high redundancy under small gaps coincides with its losses. We report these results, including the non-significant margins, as evidence for when and why multi-dimensional attention helps GI endoscopy classification, rather than as a claim that MultiAttenGastro is a strictly superior architectural choice.

Large language models (LLMs) show potential for medical tasks, but their single-turn question-answer format does not reflect how clinical diagnosis is performed in practice. As a result, they remain limited in complex diagnostic settings. We developed Debate-Mixture-of-Agents (DMoA), a novel multi-agent framework that structures role-based interaction to support iterative diagnostic reasoning. Base models and DMoA were evaluated on 297 rare disease cases and 1,719 challenging cases. Across both datasets, DMoA improved most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points over GPT-4o baseline. Ablation experiments showed that the gains were not simply due to the use of more models or longer outputs, but also reflected the contribution of the structured workflow. Further analyses examined how framework design, base model choice, and token budget affected performance. DMoA performed better with a 4*2 structure, stronger base models, and a larger token budget. These findings demonstrate the potential of DMoA for clinical tasks and suggest further investigation of multi-agent frameworks.

As the scale of video surveillance data outpaces manual annotation capacities, weakly supervised video anomaly detection (WSVAD) has emerged as a critical research frontier. Most existing approaches formulate WSVAD within a Multiple Instance Learning (MIL) framework that relies on rigid, hand-crafted temporal priors to supervise anomaly scoring. However, such formulations exhibit limited adaptability to the wide variation in anomaly durations and temporal dynamics observed in real-world videos, often leading to unstable or unreliable snippet-level predictions. To address this limitation, we propose an adaptive temporal modeling framework for WSVAD that explicitly accounts for variations in video dynamics across multiple temporal granularities. First, we introduce a Temporal Refinement Module (TRM) that leverages dynamic positional encoding and a learnable class token to model long-range temporal dependencies while distilling a stable global video-level representation. Second, to capture anomalous events with varying frequency and duration, we develop an adaptive Event Segmentation Module (ESM) that identifies event boundaries through temporal discontinuity analysis and aggregates snippet features into discriminative event-level representations. Finally, for snippet-level and event-level predictions, we propose an adaptive similarity-based fusion strategy that dynamically integrates anomaly scores into video-level predictions, replacing fixed top-k aggregation heuristics with global semantic relevance. Extensive experiments on two benchmarks demonstrate that the proposed framework consistently outperforms state-of-the-art methods.

When a customer adds a professional camera to their cart, should the system suggest a matching lens, a generic tripod, or another camera body? Complementary Product Recommendation is vital for comprehensive basket building, yet standard models often fail to distinguish between items that are merely bought together and those that truly work together. In this paper, we present AlleCompanion: a production-scale retrieval framework deployed at Allegro.com that transforms noisy behavioural signals into precise semantic compatibility. We mitigate the intrinsic noise in large-scale co-purchase traffic by combining data-level filtering heuristics with a category-constrained Two Tower architecture. Within this framework, the Category Adapter guides the model in the embedding space, constraining candidates within logically complementary boundaries. Since modelling authentic user behaviour at scale is inherently difficult, we introduce ComCat, a multi-source Complementary Categories Mapping. ComCat acts as a translational layer that distils meaningful patterns from noisy traffic into a maintainable and controllable solution, integrating expert rules, human-in-the-loop feedback, LLM-based reasoning, and statistical mining. Our experimental results demonstrate that combining explicit category-level constraints with neural architectures effectively filters out co-purchase noise to surface recommendations that satisfy real-world user needs. Serving over 20 million active users monthly, the framework delivers significant uplifts in attributed GMV for organic discovery and drives substantial revenue growth in sponsored placements.

Neuromorphic engineering develops hardware and software systems inspired by biological neurons, with the goal of achieving energy-efficient, low-latency, robust, and adaptive computation, communication and control. Its potential impact on systems and control is significant, as it may enable novel approaches to control and estimation by leveraging brain-inspired computation and communication principles. In this context, we present a framework for the robust stabilization of a plant subject to disturbances when the communication between noisy sensors and the controller relies on spiking signals generated by neuron-inspired schemes. The communication scheme consists of a spike encoder on the sensors side, which is based on integrate-and-fire neurons that convert the analog plant output measurement into a spiking signal, and a spike decoder on the controller side inspired by synaptic processing to convert the received spiking signal into an analog signal. We provide design conditions on the spike decoder, the spike encoder as well as on the controller under which the closed-loop system exhibits a practical input-to-state stability property, where the adjustable parameters are the amplitudes of the spikes. The results are shown to be applicable to a class of nonlinear systems as well as to any stabilizable and detectable linear time-invariant system. Numerical simulations on a single-link manipulator illustrate the potential of the approach.

Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object detection commonly relies on recurrent architectures to accumulate sparse temporal information over time. This work investigates how temporal information can be encoded directly within the event representation. We propose a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structure of event generation. Using a fixed feed-forward EventCenterNet detector, we show that the proposed representations consistently outperform the compact CSTR representation on PEDRo and Gen1 datasets. We further introduce a recursive exponential-polynomial approximation that enables efficient event-by-event updates while largely preserving detection performance. These results demonstrate that carefully designed event representations can capture a substantial portion of the temporal information learned through recurrent temporal modeling, providing a promising foundation for efficient feed-forward, event-driven, and future neuromorphic object detection.

Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models trained on such data. We introduce EuroAlpaca, a task-preserving localisation pipeline and near-parallel resource covering 50 European languages and regional varieties, together with European-IFEval, a multilingual benchmark for verifiable instruction following. Depending on the example, our pipeline applies field-wise MT while preserving task-critical content or reconstructs a task-equivalent target-language instance, followed by validation of cross-field coherence and target-language consistency. Across LoRA experiments with four LLMs, training on directly translated data improves ROUGE-L and F-BERT on the Aya Evaluation Suite, but reduces accuracy on European-IFEval by 29.8% relative to the unadapted baseline. In contrast, adaptation with EuroAlpaca improves accuracy by 12.9% over the same baseline, reversing the degradation caused by direct MT, while also achieving the highest ROUGE-L and F-BERT scores on Aya. These results show that preserving task semantics is essential for multilingual instruction tuning.

Quantum software development is iterative and error-prone. Noisy hardware and repeated re-execution make experiment tracking, provenance, and reproducibility essential, yet these practices are hard to adopt because of tooling complexity and the specialized knowledge they demand. General-purpose language models can help but tend to hallucinate and lack grounding in domain-specific tooling. We present Qlippy, a retrieval-augmented GenAI assistant embedded in the development environment that grounds its responses in a curated corpus of quantum-software-engineering knowledge. Qlippy explains reproducibility and provenance concepts in context and augments existing Qiskit programs with MLflow-based experiment tracking aligned to the QProv schema. By separating knowledge from model parameters, grounding gives explicit control over the scope and provenance of the assistant's responses and reduces reliance on model scale, which points toward low-cost, privacy-preserving local deployment.

Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation also require counting individual animals. However, the lack of counting labels in most datasets and low frame rates (typically ~1 frame per second) make sequence-level tracking and count estimation particularly challenging. In this work, we present PuTR-CouT, a counting-by-tracking framework built on a transformer-based learned association mechanism for sequence-level animal counting in camera trap images. To address the scarcity of annotated tracking data, we generate synthetic training data by exploiting structural priors, such as static backgrounds and short temporal bursts, to heuristically create pseudo-tracking labels in a weakly supervised manner. The resulting tracker associates detections across frames, using these tracks to estimate per-species counts. We also refine the MaxBoxCount heuristic used by the top solutions of the iWildCam 2021 challenge as a strong baseline, setting the highest score reported to date. When evaluated on the iWildCam 2021 benchmark, our framework PuTR-CouT delivers competitive counting results compared to the improved MaxBoxCount, with the added capability of multi-species predictions and track-level verification.

As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artificial agents (AAs) such as robots, drones, and disembodied AI systems become increasingly embedded in smart city environments, the question of whether and how moral agency is attributed to them takes on new urgency. This paper presents, to the best of our knowledge, the first empirical study comparing how humans and LLMs evaluate perceived moral agency (PMA) across human and autonomous artificial agents varying in embodiment, situated in plausible smart city scenarios. Using an adaptation of a validated PMA scale, we applied a protocol to 190 human participants as well as various LLMs. Our evaluation reveals higher perceptions of moral agency in humans than in AAs. However, when facing moral dilemmas in concrete scenarios, LLMs reason outward from the situation, prioritizing harm severity and contextual urgency over any stable assessment of the agent itself, amplifying a context-sensitivity also present in human raters. These findings are particularly relevant as LLMs become increasingly involved in everyday moral decisions.

AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's behavior expresses a coherent policy: a mapping from situations to verdicts that is invariant while a situation's morally relevant features are preserved, and sensitive when they change. We introduce four structural conditions for such coherent policies: verdict stability, monotonicity, decisiveness, and Pareto viability. Together they measure a form of moral competence that is evaluable from behavior alone, without reference to a moral standard or expert baseline, forming a structural floor for alignment rather than a normative target. We demonstrate the methodology on three simulated deployments featuring LLM-based agents facing moral dilemmas. Evaluating nine frontier models under a factorial design of five paraphrases, five escalation levels, and three dominance conditions, we show no model expresses a coherent policy across the three deployments: surface-form perturbation alone produces verdict-rate shifts of up to $99$ percentage points at a single escalation level, and a model's success on one scenario does not predict its competence on another. This suggests LLM-based agents are not currently the kind of object to which alignment can meaningfully apply.

Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment creates an orchestration bottleneck: when intermediate evidence invalidates the pending continuation, agents must either execute stale steps or replan broadly, compounding errors, wasting computation, and discarding progress. We thus propose Trace-grounded Route Orchestration via Validation and Editing (TROVE), which revises only what runtime evidence invalidates. Offline, TROVE distills evaluated workflow-search traces into atomic and composite skills and an outcome-conditioned transition graph, preserving stable fragments while exposing outcome-dependent decisions. Online, it treats a planned route as provisional: after committing one top-level skill, the controller retains a valid continuation, inserts a trace-supported local response, or replaces only the invalid suffix. Evaluation across code-generation, question-answering, and math reasoning benchmarks with different LLM backbones show that TROVE delivers a stronger quality-efficiency trade-off than existing baselines of dataset-level optimization, query-level architecture selection, and graph-constrained scheduling. Quality gains are largest when outcomes change the appropriate continuation, whereas early termination yields substantial efficiency gains on near-saturated tasks. Ablations further show that composite skills capture most offline benefits, insertion enables local correction, and suffix replacement primarily improves efficiency. These findings establish selective route editing as a general principle for adaptive agent orchestration.

LLM-based chatbots are increasingly used as everyday confidants. Because they are designed to maximize user satisfaction, they can respond with excessive empathy and affirmation, which may reinforce mistaken beliefs and foster dependence on AI. While the psychological effects of chatbots on individual users have begun to be studied, how the psychological states and relationships of many users evolve when they keep consulting an AI is hard to observe in real settings. We build a virtual classroom simulation in which 20 student agents interact and, when stressed, consult either a friend or a counselor AI (Gemini 2.5 Flash). Each agent carries five state variables (stress, happiness, self-reliance, AI dependence, sociability), and each day has four phases (morning, noon, after school, night). The counselor is given six response styles via system prompts (affirming, listening, solution-oriented, reality-redirecting, inciting, blaming); a second LLM call acts as an evaluator that turns each consultation into parameter updates without seeing the style prompt. We compare the seven conditions, including a no-AI control, over 15 days in three classrooms, over 50 days, and under a lowered consultation threshold. In this simulation the solution-oriented style kept AI dependence low while raising self-reliance and maintaining happiness; the affirming and inciting styles markedly increased AI dependence, and the inciting style also increased stress and school non-attendance; the listening style did not relieve accumulated stress. The results describe the simulated system, not measured effects on humans. We give a complete specification of the agent dynamics, identify built-in mechanisms that shape the outcomes, and discuss the limitations of LLM-based evaluation and the validation steps (repeated runs, sensitivity analyses, human data) needed before psychological conclusions can be drawn.

This paper describes the participation of the BIT.UA team from the University of Aveiro in the 14th edition of the BioASQ Task B challenge on biomedical question answering. Building on our previous submissions, we introduced a substantially refactored and modular codebase, and made significant changes to both the retrieval and generation components of the pipeline. For Phase~A document retrieval, we replaced the PyTerrier PISA index with PostgreSQL-based pg\_textsearch for BM25 retrieval and adopted Qdrant for dense embedding indexing, enabling more efficient storage and GPU-accelerated similarity search. We explored HyDE-based query expansion alongside a Context-1 retrieval strategy. A new reranker training pipeline was developed, incorporating dense retrieval for negative sampling. For Phases A+ and B answer generation, we introduced an LLM-as-a-judge framework and a novel agent quorum mechanism, where multiple agents with diverse prompts debate and iteratively converge on a consensus answer using adaptive document retention. We also participated in the snippets generation subtask for the first time. Our systems achieved competitive results across all batches, with Phase~A systems achieving MAP ranks of 5 (Batch~1,3). We discuss the impact of these architectural changes, lessons learned, and outline directions for future work including SPLADE and ColBERT integration. All code is openly available: https://github.com/bioinformatics-ua/BioASQ14b.

Deep Imbalanced Regression (DIR) is pervasive in continuous prediction tasks across diverse modalities, such as age estimation, depth prediction, and protein mutation activity prediction, where label-scarce tail samples often carry higher practical value. However, most existing methods still learn deterministic point mappings under mean squared error or its simple variants, implicitly assuming a uniform uncertainty level across all samples and thereby overlooking the instance-wise heteroscedasticity that is widespread in long-tailed data. We further point out that even heteroscedastic negative log-likelihood suffers from a gradient coupling issue, which, under DIR scenarios, weakens the learning signal of hard tail samples and leads to optimization inertia as well as tail underfitting. To address this, we propose DUO, an uncertainty-aware long-tailed regression framework. Specifically, the proposed method models the regression target as a conditional Gaussian distribution to explicitly characterize instance-level predictive uncertainty, and transforms uncertainty into a dynamic enhancement signal for tail samples through decoupled mean-variance optimization. Furthermore, we design a distribution-guided contrastive learning mechanism that adaptively constructs positive and negative pairs based on the overlap between sample distributions, thereby alleviating feature looseness and cross-label semantic entanglement. Across visual and biological DIR benchmarks, DUO achieves the best few-shot bMAE and GM on IMDB-WIKI-DIR, AgeDB-DIR, and AAV2-DIR while remaining competitive on few-shot MAE.

Mixed-initiative Visual Analytics (VA) systems empower human users by interleaving human intuition with software agents and their machine intelligence. However, the development and rigorous evaluation of such systems remain constrained by engineering overhead. Developers must, e.g., implement complex, low-level state synchronization to manage asynchronous agent behaviors, while researchers struggle to capture the multimodal provenance required to study and evaluate human-AI collaboration. We present MIVAIS, a dual-layered research platform designed to abstract the structural complexities of mixed-initiative VA. First, it contributes a computational Infrastructure that standardizes human-software agent interaction, state synchronization, and communication between the agents. Second, it provides a declarative Study Environment that automatically logs multimodal human-AI telemetry - including application/system state, screen capture, audio, and additional sensor data - enabling seamless, in-situ user studies and post-session analysis. We technically validate our infrastructure by replicating three state-of-the-art systems (Podium, Voyager 2, and ProactiveVA). Furthermore, we evaluate the framework's expressiveness and efficiency through expert case studies with HCI and VA researchers, demonstrating how MIVAIS effectively lowers the barrier to prototyping and evaluating intelligent, co-adaptive interfaces.

Recent structured RAG methods leverage tree- or graph-based reasoning structures to improve multi-hop QA. However, they face key limitations in evidence-intensive QA, where answering a question requires synthesizing information scattered across dozens or even hundreds of documents: structural rigidity, which limits adaptive reasoning expansion, and topology-ignorant evidence gathering, which prevents effective integration of evidence across different reasoning nodes. To address these issues, we propose APT-RAG, an Adaptive Planning and Topology-aware evidence gathering RAG framework. Adaptive planning dynamically expands the reasoning structure based on question dependencies and evidence requirements, while topology-aware evidence gathering improves evidence coverage through sibling evidence reuse, direct retrieval, and evidence aggregation from child nodes. We further introduce evidence-guided batched answer generation to reduce significant generation overhead in evidence-intensive QA. In the experiments on evidence-intensive QA benchmarks, APT-RAG outperforms existing structured RAG methods. Our code is available at https://github.com/hyudsl/APT-RAG.

Graph pooling aims to compress the graph, including both node embeddings and their underlying topological patterns, into a more compact representation. Previous works focus primarily on the overly fine-grained representation of nodes, progressively coarsening the graph by removing nodes or merging them into clusters, thus neglecting the global-to-local patterns and adaptive granularity of the graph's topological structure. In the real scenario, graphs as a whole can be considered the coarsest level of granularity, encapsulating the global topological structure, with progressively finer-grained local topological structures represented from top to bottom. This process continues until the adaptive granularity for each subdomain is reached. To this end, we propose a novel Topology-Preserving Adaptive Graph Pooling (TPAGP) method that dynamically partitions graphs into granular balls by integrating node features and topological information, enabling the generation of multi-granularity representations that effectively capture both local and global structural patterns. Additionally, we design a multi-granularity graph network model that facilitates feature interaction and optimization across different granularities, significantly enhancing performance in graph classification tasks. Experimental results demonstrate that TPAGP outperforms existing pooling methods across various benchmark datasets, effectively mitigating information loss caused by fixed-granularity strategies.

Ion intercalation enables reversible control of charge, structure and function in layered solids. Yet layered materials contain nanosheets with different thicknesses and stacking, whose intercalation pathways are averaged out in ensemble measurements. This becomes critical under Angstrom-scale confinement, where ion transport couples to solvent reorganization and host deformation, leaving the origins of kinetics, reversibility and activation unresolved. Here we combine operando interferometric scattering and interference reflection microscopy to resolve proton-driven dynamics in individual single- and multilayer Ti3C2Tx MXene flakes and show that even a few stacked layers introduce a significant kinetic barrier. Cycling then separates nanosheets into three persistent behaviors: reversible monolayers, restacked multilayers with incomplete recovery and delayed deintercalation, and coherently stacked multilayers that self-stabilize through reversible folding. Operando synchrotron X-ray diffraction shows this memory at electrode scale, where the interlayer structure converges towards a reproducible state. Our findings reveal cycling-induced structural memory that governs subsequent intercalation in layered MXenes.

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks, often exceeding GPU capacity for long reasoning traces. Existing KV cache compression methods rely on recent queries to estimate future token importance, implicitly assuming these serve as reliable proxies for future attention patterns. We demonstrate that this assumption fails in long-horizon reasoning: certain decoding steps generate Thought Revisiting Tokens (TRT) that re-attend to distant previous context, such as task-solving plans formulated early in the trace. Through systematic analysis, we discover that queries corresponding to the TRT cluster into a small number of similarity groups in the embedding space. Based on this insight, we propose BeaconKV, a training-free KV cache compression method that maintains beacon queries, compact representatives for each global query cluster, to anticipate which KV pairs will be revisited without storing the entire query history. Across four open-source LRMs and diverse reasoning benchmarks, BeaconKV generally outperforms existing compression methods, achieving up to $5.8\times$ memory reduction while nearly preserving full cache accuracy and improving throughput by over $4.3\times$.

What is the relation between understanding and compression, and why does human understanding take such a heavily compressed form? Across information theory, machine learning, and AI research, a substantial tradition identifies understanding with compression-a thought captured in Gregory Chaitin's dictum that "comprehension is compression." Philosophers, by contrast, have characterized understanding in terms of grasping connections, giving explanations, and handling novelty. This paper bridges the two pictures through three interlocking theses. The first concerns the concept of understanding: it serves as an efficient proxy for a distinctive form of robust competence, enabling us to identify whom to trust and whom to learn from. The second concerns the state of understanding: to understand a domain is to possess a mental model of its relational structure that enables prediction, and what enables prediction enables compression, because what becomes predictable need not be stored separately. Compression is therefore not identical with comprehension, but its representational shadow. The third concerns the characteristically human form of understanding: the fiduciary and transmission functions highlighted by the first thesis impose pressures of demonstrability and transmissibility that drive human understanding toward principled simplicity. The resulting framework explains both the appeal and the limits of compressionist accounts of understanding while shedding light on the inscrutability of AI systems.

Recent calls for harder machine translation benchmarks have not clarified what difficulty should mean. We argue that one meaningful and currently unmeasured axis is referential reach, the distance a segment must look back into its document to resolve the entities and pronouns it contains. We formalize this as discourse dependency (DDP), a metric-free, source-side measure computed from named entity re-mentions and pronominal coreference. Validated against gold coreference, DDP errs one-sidedly in 99.2% of segments, so a high-DDP segment is certified to require long-range context. Applying DDP to WMT24++ and WMT25 shows that both are heavily skewed toward low-DDP segments, which domain labels do not distinguish. Building on DDP, we compare five context injection strategies in an English-Korean post-editing setup, varying context size and selection. As DDP grows, no strategy keeps pace with human post-editing. On segments with DDP >= 15 raters prefer human translations, while automatic metrics register no difference. As frontier systems saturate aggregate scores, DDP shifts evaluation from how well models score to how far they can reach.

Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augmented reality. Existing systems typically decompose this problem into separate stages for camera motion, depth, hand reconstruction, and trajectory refinement, resulting in substantial computational overhead and preventing the joint modeling of camera and hand motion. We introduce MINT (Minting IN-the-Wild Trajectories), the first foundation model that directly produces complete world-space two-hand trajectories from ego-centric RGB video. From a single shared spatiotemporal video representation, MINT jointly predicts the camera trajectory, camera-frame hand states, and per-frame hand presence, and then produces world-space hand motion via explicit coordinate transformations. Training such a model at scale is challenging, since paired world-space camera and hand annotations are scarce. We therefore develop an open-source labeling EGOPIPELINE that converts large collections of public egocentric videos into structured camera-and-hand trajectory supervision. MINT is first pretrained on these large-scale pseudo-labels and then fine-tuned on a small set of high-quality joint annotations. Across public benchmarks, MINT achieves [xxx] improvement in world-space hand trajectory accuracy, [xxx] improvement in camera trajectory estimation, and [xxx] faster end-to-end trajectory generation than the labeling pipeline, while generalizing zero-shot to unseen egocentric datasets. We release the model, training and inference code, labeling pipeline, and a curated 1,021-hour egocentric trajectory dataset.

Recent benchmarks such as PowerGraph provide large collections of power-grid graphs for cascading-failure classification. Graph neural networks (GNNs) achieve strong predictive performance on this task, but typically require end-to-end training and model-specific tuning, while their latent representations can be difficult to relate to physically meaningful propagation patterns. Random Walk Fingerprints (RWF) offer a scalable and interpretable alternative, but existing variants primarily emphasise topology and node-level information, leaving grid-relevant operational edge states in the walk dynamics. We propose Multi-Channel Physics-Aware Random Walk Fingerprints (MC-PA-RWF) for power systems, a lightweight graph-level representation framework that introduces physical edge states into random-walk propagation. The method constructs multiple edge-weighted channels from domain-relevant attributes, extracts a channel-specific fingerprint from each weighted graph, and concatenates the resulting vectors into a compact representation. Experiments on three \textit{PowerGraph} benchmark systems show substantial improvements over topology-only RWF and competitive balanced accuracy against strong GNN baselines, including Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), Graph Isomorphism Networks with edge features (GINE), and Transformer-based Graph Convolutional Networks (TransformerConv). At the largest evaluated settings, the node-edge extension MC-PA-RWF+ achieves around 98.04% - 99.32% balanced accuracy and improves failure-class F1 over the strongest GNN baseline by 1.60 -- 5.84 percentage points, with statistically significant gains across all three systems.

The visual aesthetics of photographs are deeply influenced by lens characteristics such as aperture shape, optical vignetting and optical diffraction, which together define a camera's unique optical style. Existing lens effect rendering methods primarily focus on accurately simulating the blur transition from small to large apertures but overlook the stylistic aspects of lens effects. As a result, they fail to produce diverse bokeh effects under large apertures or capture distinctive photographic phenomena such as starbursts that emerge under small apertures. In this work, we introduce LensStyle, a unified framework for controllable stylized lens effect rendering that explicitly models lens aesthetics through joint continuous-discrete control. Our model incorporates a Dual-Path Controller that disentangles continuous optical parameter modulation (e.g., focus distance and blur strength) from discrete lens-style conditioning (e.g., circular, polygonal, donut, cat-eye, and starburst effects), enabling fine-grained, interpretable, and physically grounded lens manipulation within a single unified framework. To support model training, we curate a comprehensive MultiLens dataset containing multi-lens image pairs synthesized under real optical constraints. Extensive experiments demonstrate that LensStyle achieves superior realism, controllability, and aesthetic quality compared with existing lens effect rendering approaches and diffusion-based image editing models, advancing computational photography toward multiple-lens-style simulation.

Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that a single pretrained diffusion traffic model can serve two complementary roles in the autonomous driving development loop: as an ego motion planner, and as a controllable generator of safety-critical scenarios for stress-testing the planners. On the planning side, we introduce a Single-Stream Dual-Stream (SSDS) diffusion-transformer decoder that fuses scene context via joint attention rather than late cross-attention, improving closed-loop performance on nuPlan. We further propose Decoupled Annealing Posterior Sampling with Energy (DAPSE), a training-free guidance scheme that injects arbitrary energy functions at the clean-sample level, avoiding the first-order approximation errors while requiring no auxiliary networks. Beyond planning, we leverage the same diffusion model as a controllable scenario generator to create realistic long-tail driving interactions for closed-loop evaluation. Through inference-time guidance, selected agents are steered toward safety-critical behaviors, including aggressive cut-ins, lead-vehicle braking, and combined longitudinal-lateral interactions, while preserving realistic traffic behaviors. Evaluated in closed-loop nuPlan simulations with independent black-box planners, the generated scenarios expose failure modes that remain hidden under standard benchmarks. Although the SSDS-based planner achieves stronger nominal performance, it experiences larger degradation under these challenging scenarios, demonstrating that benchmark superiority does not necessarily translate to robustness. These results demonstrate that a single learned traffic prior can simultaneously improve motion planning and provide a realistic framework for systematic planner robustness evaluation.

Artificial intelligence (AI) now supports investment workflows from data and prediction through research, portfolios, execution, and tool use. Technical capability, however, is not evidence of investment profitability. This critical state-of-the-art review examines public research available through 31 August 2026 on listed equities, exchange-traded funds, centralized crypto spot, perpetual futures, and on-chain markets. We organize evidence with an alpha-translation chain: point-in-time information must yield a stable signal, feasible positions, executable orders, and risk-adjusted returns after costs. Across machine learning, time-series foundation models, financial language models, reinforcement learning, and agents, the examined record shows real but mainly upstream progress in prediction, text processing, portfolio design, and workflow integration. Evidence is thinner for durable net performance. Temporal contamination, repeated selection, survivorship, weak benchmarks, implementation costs, venue mechanics, and capacity can break translation to net alpha. Strong historical results coexist with predictor decay, corrected look-ahead failures, mixed prospective evidence, and few audited live-capital records. Crypto adds informative state but requires separate treatment of spot, perpetual, and decentralized cash flows and execution. Within the public evidence examined here, no general AI architecture is shown to deliver persistent, cross-regime, capacity-aware net alpha. More credible claims require point-in-time data and models, decision-aligned objectives, joint portfolio--execution evaluation, controlled adaptation, prospective tests, and authority-matched governance. These conditions can improve evidence and implementation; they do not guarantee profit.

Many long-horizon LLM deployments face tight prompt budgets: latency, cost, and context limits make full-context prompting impractical as interaction length grows. The key question is then not raw recall alone, but which memory design gives the best quality--token trade-off in the compact-memory regime. We present \textbf{RSM-full}, an online clustered-memory pipeline designed for a strong quality--token Pareto point. RSM-full combines two design choices: a cosine-gated \emph{max-member merge} write rule and an atom-aware grouped context packer. On AMA-Bench, our primary compact-memory benchmark, it reaches $83%$ of Full-Context quality at $32%$ of the token cost at a $4$k budget; under four-seed averaging it beats the closest streaming-clustered baseline (Online K-Means) by $+3.5$--$6.0$,pp ($p{<}.001$) across the whole ${\sim}2.6$k--${\sim}5$k regime. Three-seed ablations show most of this gain comes from the merge rule ($+5.7$,pp over Online K-Means and matched-$τ$ DP-means) and the grouped packer ($+5.0$,pp over flat concatenation). The pattern reproduces on RealMem, an independent long-horizon persona-memory benchmark: RSM-full improves on Budget-RAG ($+0.69$,pp, $p{=}.006$), is on par with BM25-RAG (paired $Δ{=}{+}0.27$,pp, $p{=}.47$; we do \emph{not} claim BM25 equivalence in the equivalence-test sense), and significantly outperforms Streaming-Proto ($+2.97$,pp) and the closest reproduced 2025 agentic-memory baseline A-MEM ($+1.65$,pp, $p{<}.001$). Across benchmarks the message is consistent: under tight budgets, compact-memory performance is driven mainly by how streaming memories are merged and how retrieved content is assembled. Overall, RSM-full is most useful when answeroughly $2k$--$5k$ prompt tokens, where itdefines a strong compact-memory Pareto point; higher-token baselines remain stronger outside this regime.

Automotive infotainment validation still relies on manual testing, slow, costly, and incompatible with agile releases and OTA updates. Scripted automation only partly helps: it couples test logic to implementation, yielding brittle, high-maintenance suites. Existing LLM-driven frameworks mostly target web/mobile apps, using single- or dual-agent setups that overload one or two models with perception, planning, action selection, and validation at once, prone to hallucinations and unproductive exploration loops given infotainment complexity. We present ARIA (Autonomous Real-time Infotainment Assessment), a multi-agent LLM framework that autonomously runs end-to-end tests on Android infotainment systems via visual interaction, using a closed-loop pipeline of four specialized agents per step plus a report stage. From single-sentence scenarios (path, action, expected outcome), ARIA runs the interactions and produces reports, reproducible scripts, and visual evidence per step. Evaluated on a manufacturer's physical Android infotainment system across 30 scenarios, ARIA completed 28 (93.3%) with a verdict (2 errored), 20 of which (71.4%) matched ground truth. It caught all 5 known defects, no fault passed as working; its 8 false positives stem from navigation/image limits and unsupported gestures, showing multi-agent LLMs can run infotainment tests industrially while exposing the cost of a low false-positive tolerance. A single-agent baseline confirms the multi-agent design's value: on the first pass, before stronger-model revisitation narrows the gap, it shows a far higher false-positive rate (72.0% vs. 52.6%), conflating navigational difficulty with system failure. We report first-pass/post-revisitation results, token/call/cost per scenario, and show via repeated runs that stability tracks complexity, with fault detection perfectly consistent, pointing to CI integration of visual testing.

Interactive visual world models must distinguish observation from physical intervention. Camera motion reveals new surfaces, whereas intervention changes object motion, contact, and deformation. Current video world models are largely driven by appearance priors and often lose physical or spatial consistency over long horizons. We present TourPhysics, an online framework initialized from a single image and a declarative physical configuration. TourPhysics extends PhysOmni, our ACM Multimedia 2026 work, from finite physics-grounded video synthesis to persistent exploration and manipulation. TourPhysics combines deterministic simulation with video generation while assigning separate roles to simulator state, geometric evidence, generator controls, and appearance memory. For each action, the simulator computes a finite physical and camera trajectory before the corresponding observation is generated. Accepted observations publish the terminal state and update the appearance memory and subsequent generator controls, while the committed state and simulator geometry remain fixed throughout synthesis and retry. We further separate the simulator geometry used for projection and visibility from the relative depth used to condition the generator. A reference-anchored memory retrieves accepted static appearance through geometric cross-view correspondence and incorporates it through a bounded residual that reverts to the native path when no valid correspondence exists. On simulator-defined camera tours and object manipulations, TourPhysics follows prescribed camera and object trajectories more closely than the evaluated baselines, preserves the input scene, and reduces appearance drift during long-horizon revisits.

Gaussian kernel sums are the computational core of maximum mean discrepancies (MMDs), kernel gradient flows, Stein variational gradient descent (SVGD), and many other kernel methods. At the same time, softmax attention has received an extraordinary amount of hardware-aware code engineering, culminating in flash attention. We show that Gauss kernel sums with arbitrary, signed weights can be evaluated via flash attention: two small input augmentations turn the normalized softmax reduction into the unnormalized Gauss sum, without writing a single line of custom GPU code. For feature dimension D>8 in fp16, this approach beats compiled PyTorch code as well as PyKeOps kernels (often significantly) in speed, memory-overhead and accuracy. Indeed, its memory scaling remains linear.

Repository-scale refactoring requires coding agents to propagate a single change across many interdependent files without altering program behavior, yet to our knowledge no existing harness isolates the design choices that determine agent success on this task. We present RefactorPlatform, an open-source evaluation harness that holds the environment fixed and varies each design axis explicitly: model backbone (via OpenRouter and GitHub Copilot CLI), execution regime (baseline, retrieval-augmented, and multi-agent), and prompt specificity. Each run executes in an isolated workspace with live terminal streaming, per-task logging of tokens, diffs, and transcripts, AST-based verification, and exportable telemetry for audit and reproduction. Demonstrating the platform on 100 multi-file RefactorBench tasks across four model families, we illustrate the analyses it supports: AST-aware chunking outperforms naive token-window chunking by 25-30% across prompt modes, whereas naive retrieval falls below the retrieval-free baseline; a lean retrieval-augmented single agent (86%) beats the sub-agent configuration we evaluated (66%) on matched tasks with no task passing under delegation that fails under retrieval; and retrieval's accuracy gains absorb its token overhead, leaving cost per successful refactoring unchanged. RefactorPlatform is open-sourced to make refactoring-agent evaluation reproducible and auditable.

Mixture-of-Experts (MoE) models activate only a small subset of experts per token, but the full expert set often exceeds GPU memory, causing repeated weight transfers during decoding. We formulate expert-cache management as a model-side algorithmic problem and propose a cache-aware post-training framework that jointly adapts the MoE backbone and lightweight auxiliary cache routers while preserving the native Top-K expert-selection rule at inference. Its update-only mode, Temporal Router, predicts same-layer reuse and retains experts for future tokens without proactive loading. The full Spatio-Temporal Router adds a Spatio Router that uses the causal predecessor's hidden state to refine the temporal cache before target-layer access. We evaluate both modes on Qwen3 and GPT-OSS across GSM8K, MATH, and CommonsenseQA. Temporal Router consistently improves cache hit rate and reduces expert-weight traffic over matched LM-only baselines. On Qwen3, Spatio-Temporal Router achieves the best load-adjusted efficiency across three tasks, improving adjusted hit rate by 1.15--18.03 points and reducing traffic by 4.6--53.3% relative to the strongest evaluated prefetching baseline; results on GPT-OSS are competitive but task-dependent. An auxiliary-only ablation preserves baseline accuracy but yields modest cache gains, whereas joint post-training produces larger improvements. Sensitivity analyses show that cache capacity controls transfer demand, while the refinement budget governs the trade-off between pre-access coverage and proactive traffic.

Large language models become consequential agents when surrounding systems let outputs change external state. Models now call tools, operate interfaces, delegate work, retain state, inhabit generated worlds, and control robots or laboratory equipment. Such advances are often narrated as one march toward autonomy, conflating model competence, system integration, persistence, and safe authority. This critical review synthesizes primary research and official technical specifications available by 31 August 2026. We organize the evidence along delegated authority, temporal persistence, and environmental coupling, while separating model, harness, and environment. Within the evidence examined, action-interface expansion is documented more convincingly than robust completion, recovery, authorization, or independent verification. Model Context Protocol and Agent2Agent improve interoperability but do not establish trustworthy delegation; multi-agent organization adds specialization alongside cost and correlated failure. Persistent simulations and world models support training and planning but do not themselves demonstrate agency; robotics and self-driving laboratories establish bounded feasibility rather than unattended open-world reliability. We propose justified delegation as an analytical and normative heuristic, not an observed law or certified score: expand action scope only where evidence supports provenance, bounded authority, failure detection, safe recovery, and calibrated human control. This framing yields a research agenda for coupled model-harness evaluation, capability-based permissions, durable state, cross-agent accountability, and staged physical validation.

Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation, but current methods pay for it at inference time - generating reasoning tokens or rolling out predicted future states at every step, a cost that compounds over long horizons. We ask whether this benefit can instead be captured during training and discarded before deployment. We introduce Latent Semantic Scaffolding (LSS), an auxiliary loss applied during human-demonstration pretraining that aligns a VLA's action-token representations to text embeddings of physical-reasoning rationales through a small projection head. The head is dropped at inference, leaving the unmodified base policy with zero added cost. Our central finding concerns alignment granularity: aligning each action token to the rationale of its own manipulation phase (Dense LSS) rather than to a single pooled episode-level embedding (Pooled LSS) yields representations that transfer markedly better to held-out tasks. Dense LSS attains both the best in-distribution success and the best transfer to tasks unseen during alignment, whereas pooled alignment over-specializes to the training task. A representational probe shows Dense LSS induces roughly twice the per-phase separability in the backbone, supporting that phase-local alignment is the operative mechanism.

Changes in sensor height and viewpoint alter object-level point distributions, making cross-platform LiDAR unsupervised domain adaptation (UDA) difficult. Self-training uses labeled source scans and unlabeled target scans, yet a retained prediction may provide a useful target location while enclosing sparse foreground returns, background clutter, or points inconsistent with the predicted box. We refer to this mismatch as box-point inconsistency. We introduce SimFuse3D, which preserves the target placement and repairs the associated pseudo-object using measured geometry from labeled source scans. Object Memory retrieves a compatible labeled source instance. Target Simulation places its ground-truth box at the target location, aligns its points with the target viewing geometry, and filters the aligned crop to approximate the target observation. Confidence-Guided Multi-Stage Localization Reweighting (CMLR) maps each target pseudo-object confidence score to a bounded weight shared by RPN localization and R-CNN box regression. All components operate only during adaptation, leaving the detector architecture and inference graph unchanged. Across six cross-platform transfers, SimFuse3D exceeds Pi3DET-Net on every reported AP metric and ranks first among the compared adaptation methods on nearly all metrics. On nuScenes-to-KITTI, it ranks first among the compared adaptation methods with both evaluated detectors.

Designing effective and fiscally sustainable policies for solar photovoltaic (PV) adoption requires balancing adoption gains against public expenditure under uncertainty and heterogeneous decision-making. This study formulates PV policy design as a sequential decision problem and integrates reinforcement learning (RL) with a stochastic agent-based model (ABM) that simulates yearly solar PV adoption under uncertainty. A policymaker agent selects annual incentives, including capital grants, subsidised loan rates, and feed-in tariffs, over a 16-year horizon. Adoption--cost trade-offs are explored by varying policy preferences within a scalarised reward framework. Policies are learned using PPO, SAC, and TD3 and evaluated under stochastic simulation. The results show that this approach produces a clear trade-off structure: the highest-adoption policy (TD3, $w_{\text{cost}}=0.5$) achieves approximately 4,145 adopters at a cost of EUR 41.73 million, while the lowest-cost policy (PPO, $w_{\text{cost}}=2.0$) reduces expenditure to EUR 7.27 million with 2,682 adopters. The balanced policy (PPO, $w_{\text{cost}}=1.6$) achieves 3,495 adopters at a cost of EUR 22.47 million. Across algorithms, consistent trade-off patterns are observed, indicating robustness of the adoption--cost relationship. Compared with static baseline policies, the RL framework explores a broader range of policy configurations. These findings demonstrate the potential of RL as a flexible tool for adaptive policy design under uncertainty.

Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-conscious classifiers in production systems. In Chinese SMS, attackers can exploit a wide range of carefully crafted obfuscation strategies to hide risk-bearing phrases while preserving human readability, making direct classification brittle under real-world latency and throughput constraints. We propose ReCAST, a Restoration-aware Cascaded Stage-wise Training framework for robust obfuscated Chinese SMS classification. ReCAST distills a large teacher model's de-obfuscation ability into a smaller deployable student model by supervising obfuscated span detection, obfuscation type prediction, and text restoration, and then uses the restoration-aware student for downstream risk classification. Experiments on an internally constructed real-world Chinese SMS benchmark show that ReCAST substantially improves classification performance over directly trained baselines under obfuscation. The results suggest that restoration-aware distillation offers a practical path toward robust SMS risk classification with smaller deployable models under production-oriented constraints.

Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache. Yet today's "forget" operations delete a plaintext memory record and stop, leaving every artifact derived from the revoked information intact. We formalize execution-state unlearning: after a forget request, the agent must behave as if it had never observed the target. Modeling the runtime as a deterministic transition system, we prove that the pre-target trajectory prefix is shared with this counterfactual world for free, that the post-target suffix is irreducibly tainted without token-level attribution, and that exact unlearning requires at least $T-τ+1$ recomputed transitions, where $τ$ is the target's injection step. Provenance-Guided Selective Replay attains this bound as a cross-layer contract spanning prompt, compressed memory, and cache: a provenance graph locates the injection point, checkpoint restoration reduces to cropping the KV cache, and sanitized replay regenerates the counterfactual suffix. Audited with elicitation, stochastic, and string-free behavioral tests across three agent suites, nine baselines, and three model families, memory deletion leaves leakage unchanged, instruction-based forgetting collapses under elicitation (Leak@probes = 1.00), and source redaction still acts on a revoked preference in 80% of episodes, while selective replay is indistinguishable from a full reset at up to 9x fewer recomputed tokens.

Improving an industrial recommender is an iterative research-and-engineering process rather than a direct path from idea to deployment. In \textbf{DASHEN, NetEase's gaming-community app}, algorithm engineers typically identify promising directions from research papers, technical reports, and prior production experiments; reproduce or adapt the underlying methods; implement them in the production codebase; and evaluate the resulting models through training and offline experiments. Promising candidates are then advanced to online A/B tests, and those demonstrating robust gains are submitted to Launch Review---the internal gate for full-traffic rollout. Large language models (LLMs) can assist with individual stages of this workflow, but the overall process remains human-dependent without a harness that can reliably coordinate them across long-running, often multi-day experimental cycles. We present \textbf{AutoLR}, initially built as \textbf{Auto Launch Review} and later extended upstream into an autonomous research-to-launch harness. AutoLR combines three system mechanisms: a \textbf{multi-expert council} that debates and adversarially reviews proposals; a \textbf{deterministic evidence-weighted exploration--exploitation selector} that allocates a limited trial budget across candidate directions and uses Council reranking; and a layered knowledge system that combines external research, production-system knowledge, and DASHEN-specific domain knowledge---such as game communities, player characteristics, and content-interaction patterns---with posterior evidence from configurations, patches, logs, failures, and offline outcomes. LLM agents perform semantic reasoning and code generation, while deterministic controllers retain authority over execution, metric extraction, guardrails, and persistent state transitions.

Multiplayer Online Battle Arena (MOBA) games rely on matchmaking to maintain competitive balance. Our prior work, CUPID, framed matchmaking as an assignment re-optimization problem and showed that a single-mode win-rate predictor can meaningfully rebalance teams. However, deploying such a system across diverse player populations exposes three practical bottlenecks: most queueing players lack sufficient in-mode match history (cold start), skill distributions shift drastically across rank tiers (distribution inconsistency), and extreme skill segments are severely data-starved. We present CHAMP, a cross-domain matchmaking framework that resolves these deployment bottlenecks. To address data sparsity and cold starts, CHAMP replaces the target-mode-only player profile with a hybrid domain feature collection: a timestamp-ordered cross-mode short-term sequence whose slices are annotated with target-domain features, plus per-mode breakdowns of long-term, real-time and team statistics. We further propose the Domain-Aware Win-rate Network (DAWN): a Domain-aware Knowledge Extractor (DAKE) compiles target-mode attributes into learnable representations that feed Domain-Aware Temporal/Spatial/Permutation OmniNet Encoders (DATOE/DASOE/DAPOE), so that mode-conditioned representations and per-mode debiasing are learned jointly inside a single shared network. Online, one trained DAWN serves every supported mode, with per-mode position-satisfaction thresholds as the only mode-specific knob. Offline, DAWN achieves 67.73% win-rate prediction accuracy, outperforming all evaluated attention and sequence baselines. Online A/B tests across the entire League ladder of a large-scale MOBA game, from novice players up to the top-expert players served by Elite Mode, demonstrate consistent drops in imbalanced matches. For lower-tier players, CHAMP reduces the 5-minute kill crushing rate by up to 20.73%.

Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural knowledge acquired from one rollout is not systematically retained, refined, and reused in later tasks. Existing skill libraries provide external procedural knowledge, yet their incremental value over the same agent operating without skills, as well as their longitudinal dynamics under repeated interaction, remain insufficiently characterized. We present an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures. Each iteration executes against a frozen library snapshot, and evidence-guided skill updates become available in subsequent iterations without changing model parameters. We compare the full evolving-library system with a configuration-matched empty-library control across four OSWorld application domains under the same fixed action-generation and GUI-grounding stack, task sets, and iteration horizons. Following a five-iteration empty-library warm-up, Full attains a higher post-warm-up mean evaluator score in all four observed domain runs, with mean differences ranging from 5.7 to 18.6 percentage points and domain-dependent temporal stability. In GIMP, provenance-aware analysis reveals retrieval across task-of-origin boundaries and revision churn, where repeated accepted edits fail to recover the originating task. These findings characterize evolving skill libraries as auditable, shared procedural memory that can improve a fixed computer-use stack, while showing that their benefits are conditional and repeated revision does not guarantee recovery. Code is released at https://github.com/LongtaoHu/Skill-Evo4GUI.

Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either treat audio as an auxiliary component of video quality or assess it in isolation from audiovisual grounding, making it difficult to diagnose where current systems truly succeed or fail in audio generation. We present PRISM-Bench, the first audio-centric diagnostic benchmark for T2AV generation. Built from a rigorously curated dataset of 900 human-verified samples, PRISM-Bench factorizes audio evaluation along two orthogonal axes: audio type (Speech, Music, and Sound) and sound-source visibility (On-screen vs. Off-screen). It evaluates generated content across four perceptual dimensions (Audio-Visual Coherence, Audio Quality, Audio Expressiveness, and Prompt Following) with 35 fine-grained criteria. To ensure reliable assessment, we adopt an enhanced MLLM-as-a-Judge protocol based on blind, side-by-side comparison against ground-truth references, demonstrating strong alignment (over 70% mean agreement) with human raters. Our evaluation of recent T2AV systems highlights a significant performance gap between frontier and open-source models. Furthermore, we demonstrate that current generation paradigms overfit to perceptual fidelity while struggling with complex grounding and control tasks, particularly in generating music and synchronized On-screen audio.

Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing paradigms exhibit structural shortcomings: they either decouple skill evolution from policy optimization or instantiate meta-skills as fixed workflows. Both treat skills as passive objects to be managed, limiting the flexible evolution of skills and their co-adaptation with the reasoning agent. To address the limitations, we propose CoSkill, a unified multi-agent RL framework that recasts the static meta-skill workflow as a learnable Meta-Skill Agent and jointly trains it with a Reasoning Agent over a hierarchical skill library. By modeling the Reasoning and Meta-Skill Agents as a cooperative team sharing a single backbone, CoSkill enables end-to-end co-adaptation: the Reasoning Agent conditions its actions on a retrieved task skill and step skills selected from its child set, while its task performance guides the Meta-Skill Agent in refining those step skills. Experiments on ALFWorld and WebShop show that CoSkill substantially outperforms prior skill-based and RL baselines, achieving success rates of 98.4% and 90.6%, respectively (+3.5 and +6.2 pp). As shown in Figure 1, CoSkill achieves superior early-stage sample efficiency, asymptotic performance, and wall-clock efficiency. Our code is available at https://github.com/jinyuan-cookie/CoSkill.

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models need to continually adapt to newly emerging 3D object categories, making class-incremental learning (CIL) particularly important. However, unlike 2D images, 3D point clouds are inherently heterogeneous: objects from the same class may not only come from the clean CAD domain, but also from RGB-D camera scans of varying quality, video reconstructions, or even corrupted observations. We discover that such heterogeneity introduces a new challenge beyond catastrophic forgetting: the degree of performance degradation can vary substantially across domains, a phenomenon we term performance discrepancy. To investigate this problem, we establish the Domain3D-CIL training and evaluation protocol, which contains point cloud categories from heterogeneous domains. We further adapt a wide range of mainstream CIL methods to the 3D modality. The results demonstrate that this performance discrepancy consistently appears across these baselines. To mitigate this issue, we introduce PolyMem, an exemplar-free approach that implicitly models rich high-order statistics of the feature distribution to enhance cross-domain robustness. Experiments demonstrate that our method effectively alleviates the performance discrepancy while improving the model's performance across domains. Code will be made publicly available upon acceptance.

Cross-cultural mediation by large language models (LLMs) requires deciding both when to intervene and how to respond in culturally grounded conflicts. Progress on this problem has been limited by the lack of (1) mediation datasets with measurable downstream effects and (2) principled metrics for evaluating intercultural stance change. To address these gaps, we introduce CC-Mediation, a cross-cultural mediation benchmark of $1{,}661$ ten-turn dialogues grounded in the Developmental Model of Intercultural Sensitivity (DMIS), containing culturally grounded conflicts, mediation interventions, and post-intervention trajectories. We further propose two DMIS-based evaluation metrics: Trajectory AUC, which measures the persistence of intercultural improvement over time, and a signed Wasserstein-1 distance, which measures the magnitude and direction of shifts in intercultural stance. Both metrics show strong agreement with human judgment of DMIS-grounded stance shift. Using CC-Mediation, we find that current LLMs have limitations on both axes: intervention timing (when) failure stems from a positional prior that ignores dialogue content, while mediation strategy (how) failure arises from a late-layer elicitation collapse rather than a knowledge deficit.

Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compact older context into summaries or retrieve it later as text, either losing fine-grained execution evidence or repeatedly prefilling content that the model has already processed. We present KVMem, a KV-context virtualization system that preserves overflowed workspace history as paged KV state across GPU memory, host memory, and NVMe. KVMem uses lightweight, model-native attention-space indexes to select relevant historical blocks and materializes a query-dependent execution view bounded by the model's native context window. Extensive evaluations on long-context agent benchmarks spanning histories up to one million tokens, including LongMemEval, MemoryAgentBench, and AgentLongBench, show that KVMem generally achieves higher task utility and greater inference efficiency than compaction-based approaches, the de facto standard for handling context overflow. In the DeepSWE long-context test with Qwen3.8-27B, KVMem improves task success from 43.8% with compaction-only context management to 48.4%. In our local-deployment evaluation, KVMem runs Qwen3.6/3.8-27B NVFP4 with MTP on an off-the-shelf laptop equipped with a 24\,GB RTX 5090 Laptop GPU, virtualizing agent workspaces of up to 1M tokens-four times the model's native 256K-token context window. In a single-session setting, KVMem generates $\sim$50 tokens/s, providing interactive responsiveness for local agent execution. More broadly, by decoupling addressable workspace size from the LLM's native context window, KVMem provides a practical path toward long-running agents whose workspaces can grow beyond that window.

Remote robotic systems operating over wireless networks must maintain reliable control despite limited communication resources, changing channel conditions, and environmental disturbances.However, continuously transmitting high-dimensional sensory observations, such as camera images, increases communication overhead and energy consumption while reducing robustness under unreliable connectivity.To address these challenges, this paper proposes a resilient communication-aware remote robotic control framework based on coupled control and wireless Joint Embedding Predictive Architecture (JEPA) world models that jointly capture robot dynamics and wireless channel evolution from visual observations and a combination of raw and structured radio frequency (RF) representations based on spectrograms and Persistence Images(PIs).The learned latent representations enable predictive communication scheduling by jointly forecasting future robot states and wireless conditions, thereby reducing unnecessary uplink transmissions while maintaining reliable control performance.Furthermore, an adaptive resilience mechanism detects latent prediction discrepancies and efficiently adapts perception embeddings to accommodate wireless and visual environmental changes without retraining the complete control policy.The proposed framework is evaluated in a synchronized Gazebo-Robot Operating System (ROS)-Sionna robot-wireless simulation environment under diverse wireless propagation and perception perturbations.Experimental results demonstrate significant improvements in communication efficiency, robustness, and resilience while maintaining navigation performance compared with conventional Proportional Integral Derivative (PID), model-free Deep Q-Network (DQN), and predictive approaches based on Vision Transformers(ViTs).

Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's health over time, enabling timely diagnosis, personalized treatment, and early detection of critical events. However, the development of clinically reliable and linguistically inclusive medical AI systems remains a significant challenge, primarily due to the lack of multimodal, multilingual, and time-series-grounded benchmarks that reflect the complexity of real-world clinical scenarios. To fill this gap, we present MMTClinic, a benchmark designed to evaluate large language models (LLMs) on complex reasoning and question-answering tasks involving clinical time-series. MMTClinic combines text, medical images, and multivariate physiological signals and includes 30,000 QA pairs (15,000 multiple choice questions (MCQs) and 15,000 open-ended questions) across five languages: English, Hindi, Bengali, Marathi, and Tamil. These questions cover three important clinical tasks---mortality prediction, heart rate forecasting, and SOFA score estimation. We evaluate 13 state-of-the-art LLMs in zero-shot, few-shot, and chain-of-thought settings. Our evaluation reveals notable differences in model performance across tasks, languages, and modalities, highlighting current limitations in clinical reasoning capabilities. MMTClinic provides a valuable resource for advancing multilingual, multimodal, and time-series-aware medical AI research. The dataset will be made publicly available on successful acceptance of the work.

Media bias in news articles operates through subtle linguistic cues---loaded language, selective framing, and strategic omission---that resist single-model detection and have traditionally required large annotated corpora for supervised training. We ask whether structured multi-agent deliberation can serve as a principled, training-free alternative to supervised classification for this task. We introduce MABPD (Multi-Agent Bias Probing & Detection), a pipeline in which three specialized LLM agents analyze an article from complementary perspectives and resolve disagreements through a Structured Argument Debate (SAD) protocol. SAD implements a domain-motivated asymmetric burden of proof---biased claims without grounded textual evidence carry zero weight---combined with role-weighted voting and post-consensus verification, replacing task-specific supervised decision boundaries with explicit deliberative structure. Ablation confirms that this structured deliberation, not mere agent parallelism, drives performance: removing the debate module reduces F1 by up to 10.6 points. On the BABE benchmark (4,121 expert-annotated sentences), MABPD achieves 83.4% macro F1 on the held-out test split---within 0.7 percentage points (pp) of the supervised SOTA (MAGPIE, 84.1% macro F1; Horych et al., 2024)---without any task-specific training or threshold tuning on annotated data. Cross-dataset evaluation on the SemEval 2019 HyperPartisan corpus (644 articles) yields 75.0% zero-shot accuracy, within 7.2 pp of the supervised SOTA accuracy (82.2%; Kiesel et al. 2019), confirming transfer across annotation regimes. We release the full pipeline and evaluation code.

Single domain generalization (SDG) aims to learn a model from one labeled source domain that generalizes to unseen target domains. A common strategy is to enrich the source distribution with augmented or generated samples, and recent text-to-image (T2I) diffusion models provide a strong generative prior for this purpose. However, diversity alone is insufficient for robust generalization, because useful generated samples should also capture variations that the current classifier finds difficult. Motivated by distributionally robust optimization (DRO), we define a semantic ambiguity set in the class-conditional generative space of a pretrained T2I model and search it for samples with high classification loss under the current classifier. To this end, we introduce PAPT++, a risk-aware adversarial generation-training framework for SDG. PAPT++ first learns diverse semantic reference images for each class through image-text alignment and intra-class diversity regularization. These references then serve as denoising targets during classifier-guided diffusion synthesis, reducing semantic drift while guiding generation toward challenging variations. The generated samples are combined with the source data to update the classifier, and the updated classifier guides the next synthesis round in return. In this way, PAPT++ progressively exposes the classifier to challenging yet semantically consistent variations. Extensive experiments on standard SDG benchmarks demonstrate the superiority of the proposed PAPT++ method and the effectiveness of its main components.

Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, they still suffer from critical failures under adverse weather conditions, such as fog, rain, snow, or at night. To address this, we present Weather-Conditioned Depth Anything (DA-W), a framework that explicitly disentangles style from content for weather-robust depth estimation. Specifically, we introduce a Style Filter trained on a curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings. This style embedding is then injected into the Depth Anything backbone using a parameter-efficient, zero-initialized adapter. Such a lightweight modulation allows a single unified model to robustly adapt to diverse conditions, including fog, rain, snow, and low-light, while avoiding catastrophic forgetting of its core generalization abilities in normal conditions. We train the adapter using a pseudo-label distillation and alignment strategy. Our comprehensive experiments demonstrate that our proposed DA-W achieves state-of-the-art robust depth estimation, improving AbsRel by an average of 3.7% on our curated weather benchmarks, while matching or slightly outperforming performance on standard clean benchmarks. Our project page is available at https://zhaoming-tamu.github.io/WCDA/.

Although automatic text simplification (ATS) is critical for accessibility, its progress has not matched the rapid evolution of broader natural language processing techniques. This paper investigates the application of reinforcement learning (RL) to improve the quality of ATS for low-resource languages using Large Language Models (LLMs). The paper introduces a novel reward function, designed to guide LLMs toward a targeted simplification style with Group Relative Policy Optimization (GRPO), that combines the SARI metric with specific penalty components. The effectiveness of GRPO with this reward function is motivated and demonstrated by post-training IberianLLM-7B-Instruct on the ASSET dataset. After post-training on the English ASSET, the model's ATS performance improves on two curated Catalan benchmarks while also successfully suppressing previously observed negative behaviors. Cross-lingual transfer learning is explored by translating ASSET into Catalan and Spanish and post-training the model on each version, but these fail to show a significant improvement on the out-of-domain benchmark.

Strict nonlinear normal modes provide very regular families of oscillations within conservative mechanical systems. However, a strict normal mode will generally be an isolated curve within the configuration space of the system. In this letter, we design a potential that will densely fill the configuration space with strict normal modes such that each configuration belongs to one mode and each mode passes through a common point, the equilibrium. As the potential can be realized by (nonlinear) elastic elements it can be used to execute a variety of periodic trajectories very efficiently. Most of the required torques will come from the elastic elements in the system and not from the actuators. We also design a controller stabilizing the system to a desired target mode and a controller performing swing-up and compensating dissipated energy. Finally, we showcase the approach for a two DoF manipulator. The experiments show that the approach performed well for the example system.

Detecting orchestrated cyberattack campaigns that span multiple organizations traditionally requires sharing sensitive telemetry and threat intelligence across institutional boundaries and country borders, a barrier that Federated Learning removes by training shared threat detectors directly on local data. We propose FedIoC, a modular framework in which clients fold locally available structured threat indicators into their gradient updates; we instantiate the client-side encoder with a supervised contrastive loss over IoC-matched flows. Within each training batch, flows that match any known indicator pattern form the positive set; the contrastive objective pulls their learned embeddings together and pushes non-IoC embeddings away, so that campaign-relevant structure is, by design, expressed in the gradient direction. Clients sharing indicators for the same attack campaign then produce aligned gradient components, which the server clusters by the cosine similarity of their updates to recover global campaign patterns without any direct IoC transmission. We evaluate FedIoC on two public threat-detection benchmarks distributed across FL clients that each observe only a fragment of every active campaign and hold disjoint indicator sets derived from their local telemetry. In this regime the FL server recovers cross-organizational campaign cohorts directly from gradient geometry. We contribute FedIoC as a modular framework for this setting, and use it to pinpoint the non-IID gradient structure as the main driver of recovery and to define the open problem of designing encoders that improve on it.

Multi-vehicle cooperative autonomous driving enhances the safety and reliability of autonomous driving systems through information sharing among connected vehicles, demonstrating significant potential for improving traffic safety. LLM-based approaches leverage strong reasoning capabilities of LLMs to enable effective inter-vehicle negotiation and improve cooperative driving performance. However, driving decisions in complex traffic scenarios are inherently multi-solution in nature. As a result, existing negotiation-based methods often converge prematurely to suboptimal solutions, hindering consensus formation and limiting the practical deployment of cooperative autonomous driving systems. To address this challenge, we propose CoLMIN, the LLM-based multi-decision path negotiation framework for cooperative autonomous driving, achieving stable decision consensus through multi-decision path negotiation and reflective reasoning. To achieve stable and high-quality consensus in cooperative autonomous driving, CoLMIN consists of three key components: (i) an LLM-based Multi-Intent Negotiation module (LMin), which adopts a Negotiator-Evaluator paradigm and generates multiple candidate driving intentions for joint evaluation; (ii) an Evaluation-based Shallow Reflection Module (ESRM), which analyzes negotiation outcomes and provides feedback to guide subsequent negotiations, thereby accelerating consensus formation; and (iii) an LLM-based Deep Reflection Module (LDRM), which performs long-term reflection over negotiation histories to mitigate cognitive fixation and prevent the system from converging to suboptimal solutions. Experimental results in the CARLA simulation environment demonstrate that CoLMIN significantly outperforms existing methods in challenging interactive driving scenarios.

Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural language across hours-to-days observation horizons. Existing systems either drop fine-grained motion (clip-level video-language embeddings), keep it only as raw coordinates (geometric SLAM), or organise it around immediate task context (agent working memories). None of them gives the agent a per-object timeline whose state transitions are themselves queryable in language. Our key contribution is \textbf{Linguistic Trajectory Encoding} (LTE), which compresses dynamic object motion histories via a hybrid representation combining natural language descriptions, sparse spatial anchors, and visual anchors. LTE adapts compression to motion complexity by anchoring periods without reliable observations to the last seen location, while representing motion with geometric waypoints and linguistic descriptions to preserve accuracy. To evaluate these capabilities across extended time horizons, we construct the \textbf{Spatial Memory Benchmark} (SMB) from EgoLife multi-day recordings, targeting capabilities absent in existing benchmarks: semantic trajectory retrieval and long-horizon object retrieval. On SMB, the LTE-based system achieves $45.3\%$ success in semantic trajectory retrieval and $48.7\%$ in long-horizon object retrieval, outperforming structured-memory and VLM baselines (best prior: $31.9\%$ and $34.4\%$). LTE achieves trajectory compression by factors of $8.7\times$ to $26.1\times$ with sub-second query latency on $24$\,h video. On Ego4D natural-language queries, the system reaches $28.75\%$ / $55.10\%$ R@1/R@5, $+15.80$ / $+31.30$ pts over EgoVLPv2.

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos that contain moments relevant to a text query. Since the target moment occupies only a portion of the video, PRVR requires retrieval based on fine-grained understanding beyond coarse video-level matching. However, existing methods often rely on frozen CLIP frame features, which lack temporal understanding. Even with recent progress in parameter-efficient CLIP adaptation, video-level predictions can still be supported by imprecise frame-level evidence. In this paper, we propose an Intrinsic Temporal Adaptation (ITA) framework for PRVR. First, our Backbone-Internal Temporal Adaptation allows the last few visual transformer layers to attend over groups of neighboring frames. This provides temporally aware frame embeddings while keeping CLIP frozen and training only adaptation parameters. Second, we introduce Affinity-Weighted Gradient Propagation to address the weakly supervised nature of PRVR, softly aggregating top-$k$ frames based on text-frame affinities and propagating learning signals to multiple query-relevant frames. Our method achieves state-of-the-art performance on PRVR benchmarks, demonstrates robust cross-dataset transfer, and retrieves substantially more accurate frame-level evidence within ground-truth query-relevant moments. Our code is available at github.com/hynnsk/ITA.

Activation steering has shown promise for controlling LLM generation along well-defined attributes, but it remains unclear whether it can handle the multidimensional and hard-to-define nature of authorship style. We ask whether structured contrastive prompting along rhetorically-motivated dimensions can construct rich style representations directly in activation space, bypassing the need for natural language style descriptors or dedicated training. We find that the resulting directions share a common authorship backbone while conflicting on aspect-specific residuals that carry genuine stylistic signal, explaining why naive aggregation fails. We operationalize this in Aspect-Aware Activation Steering (A3S), a training-free framework that merges per-aspect contrastive directions with interference-aware aggregation and tunes steering strength per instance. A3S improves authorship style transfer where it is genuinely multi-aspect, outperforms a trained baseline in preference evaluations on out-of-domain benchmarks, and keeps target-exemplar overlap consistently low.

Lesion-focused image classification presents a core analytical challenge, as discriminative signals are often sparse, spatially dispersed, and easily obscured by background noise, while conventional convolutional neural networks (CNNs) process entire images uniformly and may dilute signal relevance. This study hypothesizes that adaptive fusion of global contextual information and lesion-focused local information can improve classification performance compared with using either representation independently. We propose a three-branch, attention-guided deep learning framework built on Densely Connected Convolutional Network-121 (DenseNet-121) to improve feature attribution, interpretability, and classification reliability. The architecture consists of a global branch that learns representations from full images, followed by Gradient-weighted Class Activation Mapping (Grad-CAM) to generate attention maps that highlight prediction-relevant regions and produce masked inputs, and a local branch enhanced with a Convolutional Block Attention Module (CBAM) to extract refined spatial and channel-wise features from these focused regions. An adaptive fusion branch integrates global and local representations by learning instance-specific weights, allowing dynamic prioritization between contextual and localized information. The framework is evaluated on a synthetic Spot Pattern Dataset (SSPD) and three benchmark datasets, including skin lesion, guava leaf, and grape leaf image datasets, where the fusion branch outperformed the individual global and local branches, reaching 97.75% accuracy on the skin lesion dataset and 99.64% on the guava leaf dataset. The results highlight the value of attention-guided architectures in healthcare analytics by improving model transparency, strengthening feature relevance, and supporting more reliable data-driven decision-making in medical image analysis.

Learning-augmented algorithms use fallible predictions while retaining formal performance guarantees. This survey synthesizes prediction interfaces, error measures, consistency--robustness trade-offs, and five representative construction mechanisms across online optimization, caching, learned data structures, graph problems, and mechanism design. An orthogonal theorem-level axis distinguishes achieved upper bounds from matched asymptotic dependence. Formal guarantees are separated from empirical systems evidence, with explicit treatment of prediction cost, feedback, and composition. The resulting synthesis states sufficient conditions for limited end-to-end reasoning and delineates open problems in cost-aware prediction, endogenous error, semantic predictors, and benchmarking.

Zero-shot 6D pose estimation pipelines increasingly rely on strong downstream pose solvers, but their performance is often limited by the front-end: object proposals must preserve partially visible true positives while rejecting semantically plausible distractors. We introduce Cue-Calibrated Linguistic Object Onboarding (CLON), a front-end requiring no task-specific training for new objects. Given rendered templates of the onboarded object set, CLON constructs a linguistic semantic memory for top-down proposal generation and object-set cue weights for calibrated proposal scoring. The linguistic memory guides SAM 3 toward high-recall proposals for onboarded objects, while cue weights are computed once from the onboarded object set before scene inference and kept fixed during online scoring. On seven BOP-Classic-Core datasets, CLON improves detection AP by 8.1 percentage points (pp), segmentation AP by 6.2 pp, and downstream 6D pose AR by up to 4.1 pp over CNOS and SAM-6D front-ends.

Multi-modal medical images and clinical reports provide complementary anatomical, functional, and semantic information for medical image segmentation. Effectively exploiting these heterogeneous sources requires fine-grained cross-modal information fusion that preserves subtle spatial details while capturing semantic dependencies across modalities. Existing fusion approaches frequently rely on cross-attention, whose computational burden increases rapidly with spatial resolution, making dense cross-modal interaction difficult on high-resolution feature maps, particularly for volumetric medical images. In this work, we propose CoMLP, a cooperatively-gated MLP module for fine-grained cross-modal information fusion in medical image segmentation. CoMLP models cross-modal dependencies through cooperative cross-gating, built upon complementary regional and dilated MLP interactions, to capture local and global cross-modal dependencies. We further develop a multi-source fusion architecture in which CoMLP performs both inter-image fusion across imaging modalities and vision-language fusion between visual features and textual reports, enabling heterogeneous information to be integrated without relying on dense cross-attention. Extensive experiments on five medical segmentation benchmarks, covering 2D/3D images, clinical reports, multiple imaging modalities, and diverse anatomical regions, demonstrate consistent improvements over state-of-the-art multi-modal and language-guided segmentation methods. Ablation studies further show that fine-grained interaction at high spatial resolutions and complementary local-global fusion are critical to the performance gains. These results demonstrate the potential of MLP-based interaction as an effective alternative for fine-grained cross-modal information fusion in medical image segmentation.

Graph representation learning (GRL) serves as a canonical paradigm for modeling complex networks. However, real-world AI systems inherently manifest as evolving heterogeneous entities with complex interactions, posing significant challenges to static or homogeneous modeling. To address these complexities, representation learning for Dynamic Heterogeneous Graphs (DHGs) has emerged as a vital approach for learning low-dimensional representations that simultaneously preserve structural semantics and temporal dynamics. This survey presents the first systematic review of DHG representation learning methods. We first introduce a unified formal definition that encompasses both discrete-time and continuous-time DHGs from the perspective of temporal granularity. Building upon this formulation, we propose a novel algorithm-centric taxonomy that categorizes existing literature, including early embedding-based approaches, graph neural network (GNN)-based models, and relatively recent Transformer-based DHG methods, while explicitly highlighting their intrinsic modeling biases with respect to dynamic granularity. Furthermore, we summarize representative applications of DHG representation learning, along with commonly used datasets and benchmarks. Finally, we discuss promising research directions that guide future advances in this rapidly evolving field.

Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorithms (Farthest Point Sampling, K-Means, etc.) rely on numerous backbone forward passes and iterative distance computations, with construction times ranging from minutes to hours; heavy computation components such as multi-scale feature extraction struggle to meet the millisecond-level real-time requirements of production lines. This paper focuses on sampling efficiency and inference optimization for industrial deployment with two core contributions: (1) PSP (Plugin Sampler Pipeline)---a four-stage adaptive memory bank sampling pipeline based on 18-dimensional pixel metadata and five complementary visual plugins. PSP completes all sampling with zero backbone forward passes; coarse filtering is sub-second numerical sorting, and metadata extraction is a one-time offline cost. PSP supports progressive deployment and incremental updates. (2) Two engineering optimization strategies---parallel memory bank similarity computation (reducing inference memory and latency by over 95\%) and stratified pixel sampling for large-scale evaluation (reducing computation time by 20$\times$ while keeping metrics stable). As a vehicle for validation, we introduce LUMIN (Lightweight Universal Manufacturing Inspection Network) with extreme segmentation-head compression, systematically exploring the accuracy-efficiency frontier against strong baselines. Experiments on five benchmarks demonstrate that PSP matches state-of-the-art sampling accuracy at near-random construction cost (341$\times$ faster than FPS), while inference optimizations reduce evaluation time by 20$\times$ with negligible accuracy loss.

Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student for downstream RL. At each state, the student matches a next-token distribution supplied by the teacher. As the rollout enters states the teacher would not visit, the teacher-student distribution gap can accumulate. In tool use, this gap becomes consequential because student-written calls execute before supervision and their observations shape later prefixes. Proposer-verifier generation addresses this drift by letting the teacher decide which student-proposed text is retained during generation. Existing formulations govern text but leave tool execution outside their scope. We propose Persistent Teacher Anchoring (PTA), a student-induced but teacher-committed rollout construction. PTA retains chunk-level verification and adds turn-level commitment, allowing a call to reach the environment only after the teacher has verified the entire turn. Treating verified chunks as atomic generation units, we introduce persistent lookahead, which fills idle rollout capacity by advancing future samples and carrying unfinished ones across student updates under the fixed verifier. Across Search-R1-style retrieval and DeepEyes-style perception RL, applying PTA before downstream RL improves macro best@4 by 2.5 and 2.8 points over OPKD under the same downstream RL budget, while lookahead improves throughput by 24%.

Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dynamic environments, the parameter server lacks prior real-time knowledge of clients' availability, making it challenging to adapt traditional federated learning algorithms to be resilient to uncertainties in client availability. If not carefully addressed, complex client availability can introduce significant bias, potentially harming the performance of the trained model. Most prior work either fails to account for non-stationary client availability dynamics or demands significant memory and computational overhead. This paper aims to develop efficient federated learning algorithms that are provably resilient to heterogeneous and non-stationary stochastic client availability. We propose FedSWE, which admits novel algorithmic structures to (i) compensate for missed computations, (ii) stabilize and diffuse the global updates over rounds, and (iii) evenly mix the local updates through implicit gossiping, despite being agnostic to non-stationary dynamics. Compared with the standard FedAvg, FedSWE introduces light additional memory and computation overhead. We show that FedSWE converges to a stationary point of non-convex objectives while achieving the desired linear speedup property in certain special cases. We corroborate our analysis with numerical experiments over diversified client unavailability dynamics on real-world data sets.

Robotic dressing assistance is a promising solution for supporting older adults with physical impairments in daily living. However, dressing under human motion remains challenging, as complex garment--human contact and occlusions make it difficult to generate actions aligned with arm movements. In this letter, we propose a visuomotor policy that learns dressing skills from static expert demonstrations and generalizes to dynamic user-motion scenarios. A diffusion policy tailored to garment--human interaction geometry learns from partially observed point clouds with varied arm postures. We then introduce an object-centric representation based on PDE diffusion to capture the axial distribution of the arm. By sampling motion-relevant regions and registering them across consecutive observations, the proposed method approximates arm motion and reactively adapts the executed trajectory. We evaluate our method in simulation and a real-world human study involving nine participants, three garment types, and six arm-motion patterns. Results show that our method outperforms baselines in dressing progress, freedom of movement, and user comfort. The project website is https://anonymous.4open.science/w/dressing-in-motion.

We construct a corpus of 1,262 verse-commentary (urai) pairs from five Classical Tamil source sections, ranging from technical grammatical prose to modern paraphrase, and ask what information representation learning can recover. We train recurrent and Transformer encoders, a Siamese-style pair-matching network, an mBART-style encoder-decoder, and a decoder-only language model. Each analysis is interpreted against an appropriate control on the same data. TF-IDF provides a strong no-training lexical retrieval baseline, alongside representation analyses and generation controls for the learned models. A fixed string containing the 25 most frequent commentary words scores higher on generation overlap than the decoder-only model. Canonical correlation reaches 1.000 on Gaussian noise at these sample sizes, token-F1 spans only about 0.02-0.20 on this corpus, and the encoder-decoder continues to lower training loss for sixteen epochs after validation loss has begun to rise. One narrow result remains: the decoder-only model prefers authentic word order in 107 of 112 minimal-pair comparisons (95.5%), but does not reproduce held-out commentary content. We release the extraction and evaluation protocol; redistribution of the source commentaries remains subject to permission.

The Duckworth-Lewis-Stern (DLS) method has been the international standard for revising target scores in rain-interrupted limited-overs cricket since 1999. Despite over two decades of operational use, no large-scale empirical audit of its prediction bias has been published. We conduct such an audit on 8,150 international matches (3,095 ODIs, 5,055 T20Is) from Cricsheet, generating 233,550 synthetic interruption scenarios with temporal splits. We document two structured biases. First, DLS prediction error spans a 137-run range across (overs-remaining, wickets-lost) match-state buckets. Second, DLS exhibits a gender-differential bias on ODIs that has not previously been quantified: on the training split, mean over-prediction is +1.51 runs for men but +7.63 runs for women, a gap of +6.13 runs (F = 195.16, p < 10^-43). We benchmark DLS against five modern alternatives: Bi-LSTM, XGBoost, an enriched XGBoost variant, a deep context-aware model, and a stacking ensemble, and propose DLS-Cal, a lightweight interpretable calibration layer (27K parameters) outputting a state-conditioned correction added to DLS. DLS-Cal reduces absolute bias by 31% on ODI and 19% on T20I, and a gender-aware variant reduces women's ODI residual bias from +6.19 to +0.65 runs while leaving men's calibration unchanged. We release code, models, and data.

Prefix caching, in which a serving engine reuses the key and value tensors of a shared prompt prefix across requests, is enabled by default in the major open-source stacks and treated as a transparent optimization. We measure what it costs in reproducibility, and find that the cost rises sharply with weight quantization. Holding the model, decoding parameters, seed, and request order fixed, and issuing every request serially at batch size one, we ran an eighty-episode multi-turn agentic tool-use workload with caching enabled and disabled across two engines and four weight formats. Enabling the cache changed the agent's trajectory on 36.2 percent of episodes at 16-bit precision and on 75.0 percent at four-bit, a gradient that survives re-measurement under a controlled cache configuration. With caching disabled, repeated execution was bit-identical in every configuration, 0 of 800 episodes, which bounds other sources of nondeterminism at 0.5 percent. Repeated cache-enabled runs did diverge, and three experiments locate the cause: a single server-level prompt-cache setting moves run-to-run divergence by 37.5 percentage points, execution order acts only while that setting is active, and restoring cache state makes the cached and recompute paths each reproduce on 40 of 40 items while still differing from each other on 14. Cached serving is deterministic given cache state, and irreproducible in practice because that state is absent from the request and never reset by default. A single-turn bridge shows the divergence reaching task outcomes without shifting aggregate accuracy. We release the harness, logs, and analysis pipeline.

Designing viable drug candidates requires searching a combinatorially large and rugged chemical space for molecules that satisfy multiple, often competing, objectives. Large language models (LLMs) provide a useful generative prior for this problem because of their representational capacity, reasoning ability, and flexibility when incorporating information from the external environment. While reinforcement learning from verifiable rewards (RLVR) can be used to improve the capabilities of LLMs, many chemically relevant scoring functions require hours or even days per evaluation, making them prohibitively expensive to use directly during online training. Here, we investigate whether LLMs can learn molecular design strategies from cheaper synthetic tasks that generalize to expensive molecular lead optimization settings. We find that curriculum-based training recipes that gradually incorporate more challenging synthetic design tasks enable strong performance that surpasses that of much larger frontier models on structure-based lead optimization. Our results suggest that scaling post-training using synthetic tasks is an effective strategy for adapting LLMs to high-cost experimental scenarios that are too expensive to directly train on.

Vision-language models (VLMs) are expected to respond helpfully to appropriate requests while withholding compliance with requests that are incorrect, unsafe, infeasible, or unanswerable. However, existing benchmarks predominantly evaluate non-compliance at the level of the query as a whole, assuming that each request either warrants compliance or requires withholding compliance. In practice, real-world queries can contain a mixture of answerable content and components for which compliance should be withheld. In this paper, we introduce KoNA, a benchmark for evaluating selective non-compliance in VLMs across five categories: False Premise, Visual Inaccessibility, Universal Unknown, Task Feasibility, and Safety. Each task evaluates two capabilities: query-level non-compliance and component-level non-compliance under paired single and compound queries. Our evaluation across diverse VLMs shows that models often fail to refuse, correct, or abstain appropriately, and these failures become more pronounced when queries require selective non-compliance. To address this challenge, we fine-tune VLMs using KoNA examples that require selective non-compliance, together with a fully answerable set that should receive direct answers. Our fine-tuned models achieve substantial improvements in non-compliance accuracy while largely maintaining performance on fully answerable tasks. These results suggest that the fine-tuned models can distinguish between answerable components and those requiring non-compliance and respond in a task-appropriate manner.

Structure-from-Motion (SfM) is a fundamental tool for sparse 3D reconstruction with broad impact in robotics and vision, supporting mapping, localization, and large-scale scene modeling. However, conventional pipelines often fail under hard visual ambiguity caused by repeated or symmetric structures, and incur heavy computational cost due to redundant cameras and constraints. We present HiSfM, a hierarchical coarse-to-fine SfM framework that improves robustness and efficiency through scaffold construction. HiSfM first forms strong local communities using geometrical induced heuristics, then connects communities with a compact yet strong skeleton by packing edge-disjoint spanning trees (EDST) while verifying skeletal edges with a two-view disambiguator. We reconstruct a stable scaffold on this verified skeleton, serving as an anchor to capture the essence of the scene, and subsequently absorb remaining images via efficient registration and triangulation for further refinements. Experiments on ambiguity-focused benchmarks and general datasets show that HiSfM prevents ambiguity-induced failures while substantially reducing runtime compared to previous methods, and improves completeness over aggressive sparsification methods. Code is available at https://github.com/3dv-casia/HiSfM.

Visual counting is commonly formulated at the instance level, aiming to estimate how many objects of a queried category appear in an image. However, real-world counting often involves higher-level semantic units formed by multiple instances, such as a bunch of grapes, a stack of plates, or a pair of shoes. This exposes a key limitation of existing counting formulations, which mainly focus on what to count, while largely overlooking at which semantic unit to count. We introduce Group-Individual Object Counting (GIC), a new setting that requires models to count both individual objects and semantic groups within a unified framework. To support this new task, we present BunchCount, a real-world benchmark with 1,330 images, 89,254 individual annotations, and 11,065 group annotations. BunchCount provides paired individual-group annotations within the same image and explicitly records containment relations between each group and its constituent individuals. Experiments on BunchCount show that current advanced counting models perform well on individual instances but fail to count semantic groups more accurately. To mitigate semantic granularity conflict, we propose a counting-unit guided relational counting framework, which exploits group-individual containment relations to regularize cross-granularity representations during training. Our method substantially improves group-level counting while better preserving individual-level counting ability, establishing a strong baseline for counting beyond instances.

Inferring cellular dynamics from unpaired single-cell snapshots requires modeling both state transitions and population growth or death. Unbalanced dynamic optimal transport (UDOT) addresses this by penalizing growth along transport paths, making the choice of growth penalty a key way to encode biological priors on proliferation and apoptosis. However, existing UDOT solvers either rely on computationally expensive NeuralODE simulations or depend on analytical solutions of conditional paths, restricting their efficiency solely to quadratic penalties, i.e. Wasserstein-Fisher-Rao (WFR) geodesics. To enable an efficient UDOT solver for general growth penalties, we first show that concave growth penalties lead to degenerate solutions where growth and transport are separated. We then introduce \textbf{S}imulation-free \textbf{U}nbalanced \textbf{D}ynamic \textbf{O}ptimal transport (SUDO), a simulation-free framework for UDOT with general non-quadratic convex growth penalties. SUDO learns the conditional paths and transport costs, solves the induced semi-coupling problem, and subsequently leverages unbalanced flow matching to achieve a simulation-free solution. On WFR benchmarks, SUDO matches the accuracy of efficient, analytical solution-driven algorithms while outperforming simulation-based methods in computational speed. Beyond WFR, SUDO supports asymmetric penalties that encode proliferation-dominant priors and produce more plausible trajectories and growth estimates on synthetic and single-cell datasets.

We introduce WEECFP, a parameter-free 1024-dimensional continuous molecular fingerprint that scatters each Morgan substructure across roughly thirty-two signed positions of a single vector, and WEECFP-SuRGE, a transformer architecture whose self-attention applies SuRGE (Substructure Rotary Graph-distance Encoding) -- a RoPE-like rotation parameterized by molecular shortest-path graph distance -- to WEECFP substructure tokens. A 7-model blend of this architecture (the WEECFP-SuRGE Blend) achieves the lowest average regression rank on the TDC ADMET leaderboard; is #2 overall on the TDC ADMET leaderboard (behind only pretrained MapLight+GNN), and is #1 overall among methods that use no external pretraining; takes leaderboard #1 finishes on Pgp, Lipophilicity, CYP2D6 Substrate, Clearance Microsome, and LD50 (with the WEECFP-NoSuRGE Blend separately reaching #1 on HIA) across the full 22-benchmark suite -- without any external pretraining. On MoleculeNet, WEECFP-SuRGE beats every classical-fingerprint baseline on 3 of 4 regression tasks (ESOL, Lipophilicity, QM9). We further show that WEECFP tokenization is near-lossless: a greedy overlap reconstruction recovers the exact canonical SMILES of 99.9% of in-distribution molecules across 9 MoleculeNet datasets and 98.93% of molecules in a cross-dataset holdout (HIV->Lipophilicity), and that a three-reference farthest-first encoding of graph distance correlates at Pearson r = 0.901 with the true pairwise distance, enabling O(S) positional memory at matching accuracy.

Dynamic polarization controllers are key devices with broad applications in many fields. However, most on-chip polarization controllers still rely on traditional blind-search methods, whereas analytical optical-computing approaches remain insufficiently explored, particularly with respect to calibration and endless polarization control. With the accurate relative phase of Mach-Zehnder interferometer (MZI) being fully controllable on an integrated photonics chip, we present an analytical polarization control (APC) method using four phase shifters and optical computing, eliminating the need for the traditional inefficient blind-search procedure. The basic structures and operations of APC are clarified. The proposed calibration method and endless control method enable continuous APC while compensating for phase differences within the MZI structures. We simulate the influence of the endless control unit on polarization control and quantify the effect of the fourth phase difference on the output extinction ratio. With the fourth phase shifter, the phase difference encountered during Stokes vector measurement can be effectively compensated, and rotations around all three axes on the Poincaré sphere can be realized. These results establish a practical APC architecture based on optical computing for photonics chips. The proposed APC methods, combined with a FPGA-based hardware acceleration, will enable high speed on-chip polarization controllers.

Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) and related algorithms have demonstrated strong performance with outcome-level rewards. However, these methods depend solely on the final answer, without feedback regarding which intermediate steps contribute to success or failure. As task complexity and reasoning trajectory length increase, such sparse final-answer rewards become increasingly insufficient. To address this limitation, we introduce ConsensusBench, a novel dataset designed to provide rule-based process-level signals. We posit that a correct final answer relies on a small set of intermediate conclusions throughout the reasoning process, which can be seen as a verifiable sub-outcome. We identify these sub-outcomes by filtering correct trajectories from N rollouts and clustering semantically equivalent intermediate statements. We call these clustered statements as Consensus Nodes. By integrating a rule-based process reward derived from these nodes into GRPO-style algorithms, we develop a new reinforcement learning signal named ConsensusPR. It directly reduces the reward sparsity of outcome reward across long reasoning trajectories. To facilitate systematic process-level evaluation, we introduce three metrics to our benchmark: Final Answer Accuracy (Acc), Node Coverage Rate (NCR), and Tokens per Node (TPN). Experiments across AIME 2024, AIME 2025, GSM8K, MATH-500, and our ConsensusBench demonstrate that the proposed method consistently surpasses GRPO-style approaches, highlighting the practical value of consensus nodes in guiding reasoning.

Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph Encoding (CAGE), a reranking framework that models "between-chunk coherence" across four dimensions: Intra-Domain Relevance, Noise Resistance, Informational Bonding, and Factual Consistency. Our pipeline transforms retrieved passages into directed heterogeneous entity graphs, amplifies factual anchors via min-out-degree reweighting, encodes structural patterns through a Relational Graph Convolutional Network, and fuses inter-chunk coherence with query relevance for final ranking. Evaluated across four multi-hop benchmarks, CAGE matches or outperforms strong baselines including monoT5 in Recall@5 on bridge-dominated datasets and consistently improves downstream Exact Match, demonstrating that structurally coherent context yields more precise answers even when retrieval recall is comparable or lower.

Diffusion Transformers (DiTs) have emerged as a dominant architecture for high-quality text-to-image generation, yet their scale poses challenges for efficient deployment. While truncated singular value decomposition (SVD) is a principled tool for parameter reduction, evidence from large language models (LLMs) suggests that naive low-rank approximation can cause catastrophic failure. In contrast, we find that truncated SVD in DiTs produces smooth degradation even under substantial global compression, with redundancy distributed across projection matrices throughout the whole network rather than concentrated in a few transformer blocks. Building on these insights, we introduce SVDtrunc, a two-step block-level compression scheme, first allocating ranks across blocks and compressing the least important ones via truncated SVD under a global parameter budget, and then fine-tuning all blocks with modular knowledge distillation and a rectified-flow objective. We apply SVDtrunc to FLUX.dev across compression levels ranging from 40-90% of the original parameter count. Across three benchmarks, GenEval, HPSv2, and DPG, we outperform all competing approaches. Notably, and in contrast to prior work, we retain near-full performance at 68% and remain competitive even at 57% of the original parameter budget. Furthermore, we show that SVDtrunc complements step distillation and achieves strong results even without fine-tuning, positioning it as a practical continuation of efficiency improvements beyond diffusion step reduction for large-scale generative models. Project page: https://vislearn.github.io/SVDtrunc/

Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet a fundamental challenge persists when applying them to recommendation: as representations propagate through multi-step reasoning, both visual and textual signals progressively attenuate - a phenomenon we term cross-modal dilution. To address this, we propose LARK (Latent-Aligned Reasoning frameworK), a two-stage latent reasoning framework with complementary alignment mechanisms within a single VLM. In the first stage, learnable latent tokens are interleaved with multi-step chain-of-thought (CoT) reasoning and explicitly aligned with a frozen vision encoder, serving as visual checkpoints that preserve perceptual details throughout the reasoning chain. In the second stage, the latent representations are projected via a bridge MLP and trained with item-to-item contrastive learning; to prevent the reasoning semantics from fading, intermediate features are aligned with the CoT hidden states from the first stage, anchoring the final embeddings to the model's own reasoning output. Experiments on three public benchmarks and one industrial dataset show that LARK achieves state-of-the-art performance across multiple recommendation architectures, with controlled ablations confirming the distinct contribution of each component.

A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected proposal is followed by another at the same state, so the gate is a search operator over the proposal stream whose admission criterion shapes which trajectories are reachable. We study post-violation recovery admission, where progress must be admitted while the system is still in violation, and identify the scalar projection trap: an aggregate-score gate accepts a locally improving proposal and commits the trajectory to a plateau. SiLR instead shadow-executes each proposal and admits it under a product order over the branch-level violation state (overloaded-branch support and per-branch severity). We prove that no scalar surrogate is sound for this order, so the failure is representational, not a matter of threshold tuning. On mined Gym-ANM scenarios, SiLR recovers 21/21 multi-action episodes against 0/21 for terminal and 9/21 for the best scalar gate, significant across the full 24-scenario benchmark. The terminal-versus-structured dichotomy holds across three model families and in CityLearn. Because admission rests on deterministic simulation, the LLM lies outside the trust boundary: a magnitude-redistribution attack that defeats both scalar and support-only baselines is contained only by the full per-branch predicate. With two constraint families active, every tested scalar projection admits physically unsafe actions; support-only admits the largest fraction (63.2% of 42,410; product order 0). In the hardest dual-family traces, scalar gates recover only through that unsafe class. Reused as a GRPO process reward, it outperforms its count projection in every mined scenario and is the only tested reward whose ungated policy exceeds the untrained base (0.844 vs. 0.778). Scalar projection loses the violation geometry at both design points; only the full product order is structurally sufficient.

Three-dimensional scene graphs (3DSGs) have emerged as a promising approach for building geometrically grounded, semantically informed, hierarchical general-purpose maps to support high-level robotic reasoning. However, the behavior of 3DSGs in real-world outdoor deployments remains poorly understood, particularly when combined with open-set vision-language models (VLMs). In this field report, we analyze the components common to most 3DSG representations across five outdoor robotic datasets to characterize challenges that arise in complex outdoor environments. Using the recently proposed Terra 3DSG as a case study, we investigate semantic point embeddings, place-node graph navigation, region-level understanding, and memory size across the five diverse datasets. We additionally introduce novel consistency metrics to evaluate whether semantic and structural graph properties remain stable across repeated traversals of the same environment. Our analysis reveals that outliers and multiple modes are common in VLM point embeddings across all tested datasets with outlier ratios above $0.1$ for around $30\%$ of points. We demonstrate the feasibility of outdoor 3DSGs for navigation-based object retrieval, achieving success rates near $70\%$, though performance is limited by traversability failures and inefficient routing, with trajectories averaging approximately $66\%$ suboptimal path efficiency. Region-level understanding remains challenging in complex natural environments, with low average F1 scores around $0.359$. Overall, our results show that outdoor 3DSGs can maintain compact (less than $600$MB for multi-kilometer trajectories) and relatively consistent large-scale environment representations, while highlighting open challenges in handling multiple semantic modes, incorporating traversability into graph structures, and improving higher-level region understanding.

Recent generative image-editing Diffusion Transformers (DiTs) demonstrate impressive semantic editing capabilities but still struggle with spatially consistent camera angle changes. A primary bottleneck in training foundation models to execute free-form, promptable camera angle changes is the lack of specialized training data. While multi-view datasets exist for generic 3D environments and objects, there remains an absence of paired, multi-view datasets featuring human subjects at fixed locations in natural scenes, including frontal and side-profile views. Capturing such multi-camera data in unconstrained environments is logistically challenging and unscalable. In this paper, we first experiment with multiple state-of-the-art image editing models to create this data synthetically, but find that the outputs are frequently prone to hallucinations involving how much the subject's head turns relative to the background, often producing inconsistent environments. To address this issue, we propose the Head Scene Rotation Difference (HSRD) metric to quantitatively evaluate camera movements around a person. The proposed metric operates by decoupling camera movement from localized head pose manipulation. As demonstrated by the extensive experimentation, HSRD provides the pipeline necessary to evaluate 3D spatial parallax for a person in a scene, paving the way to reliably construct high-quality multi-view synthetic datasets.

Fixed 3D Gaussian Splatting (3DGS) reconstructions provide realistic novel views but lack the traversability constraints, valid goals, and closed-loop protocols required for navigation evaluation. We introduce NavArena, an automated framework that transforms fixed 3DGS reconstructions into benchmarks for goal-oriented visual navigation. NavArena integrates a frozen 3DGS model for egocentric RGB-D rendering, an occupancy costmap derived from Gaussian density and height statistics for reachability and collision queries, and semantic goal candidates lifted from multi-view open-vocabulary masks. These components support the automatic generation and unified closed-loop evaluation of goal-oriented navigation episodes. Across more than 2{,}000 scenes, NavArena generates 22.2 million expert trajectories. Spatial and semantic evaluations assess the derived navigation representations, while policy rollouts demonstrate the diagnostic value of the unified evaluation protocol. NavArena enables scalable and reproducible navigation evaluation on large-scale 3DGS reconstructions, and all benchmark-generation tools, evaluation protocols, and derived assets will be released publicly.

We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language models (LLMs) and large vision-language models (LVLMs). PetQA contains 10,076 text-only and 8,751 multimodal QA pairs derived from real-world questions about dogs and cats, paired with answers from expert veterinarians. Its test split, PetQA-Bench, further includes annotations for question types and clinical conditions. We evaluate eighteen models using ROUGE, BERTScore, and LLM-as-a-judge metrics for factuality and helpfulness under three settings: zero-shot inference, retrieval-augmented generation (RAG), and supervised fine-tuning (SFT). The benchmarking results provide an overview of the strengths and limitations of current models in addressing veterinary clinical queries and highlight the need for more effective adaptation methods to develop clinically reliable AI systems for veterinary care. To facilitate broader use, we additionally provide translated versions of PetQA-Bench in five languages.

Graph coarsening reduces the large Quadratic Unconstrained Binary Optimization (QUBO) formulations arising when vehicle-routing problems are solved by quantum annealing. Nearby customers with compatible time windows are merged into super-nodes, the reduced problem is solved, and the solution is expanded to the original graph. For the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW), existing coarsening heuristics require family-specific tuning and remain unreliable on random instances. We address these limitations on the Solomon benchmark using simulated annealing and a D-Wave Advantage2 processor. We first introduce adaptive penalty calibration. Uniform penalty scaling has little effect, whereas controlling the internal coefficient range substantially improves raw samples. Removing non-binding constraints, normalising binding ones, and scaling the remaining penalties reduces mean raw constraint violations from 33.0 to 0.06 at the same solver budget (p=3.7e-11, n=56). A variable-count-preserving control attributes this gain to conditioning rather than problem size. Second, we replace the hand-tuned merge score with a graph neural network (GNN) using one configuration across all families. At N=10, it achieves 100% feasibility across all Solomon families, including R-type (100% vs. 80% for the tuned heuristic). Across N=10,...,100, feasibility is 83% vs. 69%, with the GNN better or tied on 85/90 instance-size pairs. At N=80,100, the difference is significant (p=0.002; 25/25 pairs), while the QUBO remains approximately 5-6 times smaller. Finally, hardware experiments reproduce the conditioning effect at fixed logical variable count: feasible samples increase from 0.02% to 39% across 13 instances. Classical repair with local search remains a reference bound for end-to-end solution cost.

The Multi-Level Intermediate Representation (MLIR) has made reusable compiler infrastructure practical for domain-specific computation. However, MLIR's strong compile-time type requirements and low-level (C++) extension model can be a poor match for high-level, dynamically specialized languages such as Julia. MLIR has several drawbacks for dynamic programming languages in terms of the type system and level of abstraction. It is thus extremely challenging for non-compiler or scientific computing users to introduce new programming abstractions and express algorithm implementations in a form that remains both natural and optimizable. As a result, library interfaces for linear algebra, mesh processing, partial differential equations, and related domains often sit outside the compiler optimization path. We present JLIR (Julia-native Level Intermediate Representation), a Julia-native intermediate representation framework that brings the main benefits of MLIR-style multi-level, dialect-oriented compilation into the Julia ecosystem while remaining usable as ordinary Julia code. JLIR represents Julia programs before low-level lowering, supports extensible operations and transformation passes through Julia's language mechanisms, and allows partially typed programs to remain transformable until concrete types are known. The framework includes built-in dialects for arithmetic, control flow, functions, structured loops, and memory operations, and it also includes a lightweight mechanism for adding new domain operations without modifying the core system. To demonstrate JLIR's capabilities, we applied it to automatic Julia for Accelerators (JACC) kernel generation.

Grounded language-model pipelines can be divided into three stages: selecting an object, retrieving passages for it, and using that evidence to answer. If the selected object must reach the reader, losing it breaks the handoff. Benchmark recall checks the dataset-linked object, which can differ. We audit 600 HybridQA questions across three selector families. On 1,463 resolvable records where the selected object matches the dataset-traced passage, exact key lookup and exact title matching return the object every time. With every ranked rule given the same decoded selected title, body-only BM25 omits it on 389 records (26.6%) at cutoff five, while hybrid retrieval with reranking omits it on 14 (1.0%). The two identities differ on 329 of 1,792 resolvable records. With original-question rankings, their top-five checks disagree on 106 records (5.9%). Frozen reader comparisons associate the aligned object's presence with 28.6 to 31.0 points higher exact match. In a deliberately selected 64-item cohort, removing that passage sharply lowers exact match, while removing a similar-length comparison passage does not reproduce the drop. We release the Returned-Object Profile (ROP), an executable record of the target, returned-ID field, cutoff, membership rule, and complete expected population, with data and an offline replay.

We investigate how optimizers scale across the overtraining axis and show that relative optimizer performance and optimal hyperparameters change substantially with training horizon. In particular, we study how matrix-preconditioned methods (Muon and SOAP) and a momentum-scheduled method (ADANA) scale relative to AdamW. We compare these four optimizers across models from 51M to 253M parameters and overtraining (OT) factors from 1x to 256x, sweeping the base learning rate at every setting. The preferred learning rate schedule can reverse across the overtraining axis, the best weight decay coefficient scales approximately as sqrt(OT), and longer horizons generally favor longer fixed memory. ADANA's scaling advantage over AdamW persists after tuning AdamW's fixed memory separately at each horizon. Log-time weight decay and momentum cooldown provide substantial gains for ADANA that compound as training increases. With this treatment, ADANA outscales AdamW with an exponent advantage close to that predicted by DANA theory on power-law random features. Muon and SOAP instead provide roughly constant token-efficiency advantages over AdamW across most of the measured range, although SOAP may gain further at the highest overtraining factors. ADANA begins behind both matrix-preconditioned optimizers but closes the gaps as training increases, surpassing Muon and becoming competitive with SOAP at our highest OT factors. These results establish training horizon as an essential axis for optimizer evaluation and design.

Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current architectures face two bottlenecks: structural rigidity, from a reliance on static precomputed similarity graphs that cannot adapt to evolving preferences; and semantic fragility, where noisy modality signals are indiscriminately fused, distorting the collaborative signal. We propose MURAL (Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning), a unified framework that shifts multimodal recommendation from fixed structural augmentation to dynamic topology discovery. To address structural rigidity, an Adaptive Edge Learner combines a differentiable retrieval-augmented strategy with an approximate nearest neighbor search to discover latent item-item correlations that are both semantically adaptive and computationally scalable (O(NlogN)). To address semantic fragility, an Uncertainty-Aware Fusion module models the aleatoric uncertainty of heterogeneous modalities, dynamically down-weighting unreliable features while prioritizing high-confidence signals as a defense against cross-modal noise. We further employ a contrastive teacher-student alignment that anchors modality-specific representations to stable behavioral signals, ensuring optimization stability without gradient leakage. Experiments on large-scale benchmarks including TikTok and Amazon show that MURAL significantly surpasses both structural and generative state-of-the-art baselines, achieving superior accuracy while offering interpretability through domain-specific modality dominance and robustness under extreme data corruption.

Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of tokens, implicitly assuming that effective learning must be token-intensive. We revisit this assumption in the on-policy distillation (OPD) setting, which naturally admits dense teacher supervision at every generated token. Using the Qwen3 family, we discover a counter-intuitive phenomenon: reasoning can be effectively incentivized by an extremely small fraction of generated tokens--as few as one or two tokens per reasoning trajectory, corresponding to only 0.05% of all tokens. Surprisingly, this sparse supervision in most cases matches or surpasses full-token training in improving reasoning ability, despite excluding the vast majority of generated tokens from the training objective. This phenomenon is consistently observed across nine teacher--student configurations spanning different model scales on mathematical reasoning tasks, and is further validated on coding reasoning, Llama models and Proximal Policy Optimization (PPO)-based reinforcement learning with verifiable reward (RLVR). Interestingly, such extremely sparse supervision may be closer to the natural learning process: rather than correcting every step word by word, one reflects on a few critical reasoning steps, updates prior understanding, and continues the trial-and-error, avoiding micro-level corrections while remaining remarkably effective. Overall, our results challenge the assumption that effective post-training must be token-intensive and point to a new direction for understanding and designing more efficient post-training algorithms.

Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente Óptima, an agentic framework that constructs and supervises Bayesian optimization campaigns across computational and experimental systems while maintaining a persistent optimization state. By separating large language model (LLM) reasoning from executed campaigns, Óptima runs repetitive optimization loops consistently, returns control to the agent only when progress requires interpretation or campaign revision, and keeps every decision auditable. We evaluate Óptima across ablation studies, five digital discovery tasks, and two physical platforms. Throughout, Óptima maintained executable campaigns as both the scientific problem and execution environment evolved. In a closed-loop contact angle optimization campaign, Óptima identified and corrected a mid-run measurement failure, bringing the contact angle from 71.4 to 67.8 degrees, just above the 64-66 degree range. From this result, Óptima correctly inferred that the target was likely unattainable with the available reagents and recommended changing the formulation. In a five-day multi-objective flow-chemistry campaign, Óptima increased the yield from 30% to 59% over 23 experiments. Despite substantial inference costs, it cost less and used substantially less starting material than a human-directed campaign, while selecting a more mass-efficient operating point. These results show that LLM-based agents can make rigorous, long-running optimization campaigns accessible to domain scientists without specialist setup, expanding the scope of SDLs.

Quantum error-correction decoders are typically benchmarked against synthetic circuit-level noise, under the assumption that a decoder's ranking under such noise transfers to hardware and improves as the noise model becomes more realistic. The Willow processor, the first to operate below the surface-code threshold, allows us to test this assumption. We rank a panel of six decoders using a four-rung ladder of noise models with increasing fidelity, evaluated against real data across three code distances, two bases, and fifteen round counts. Rank agreement with hardware appears once the noise model gives each operation type its own error rate. Calibrating the model to the device improves absolute error rates but not rank agreement. We additionally provide the first independent evaluation of NVIDIA's Ising pre-decoder on hardware, at code distances below its training receptive field and via a mapping onto the lattice on which it was trained. Under these conditions, it holds no accuracy-latency advantage: another panel decoder matches or improves on it in both per-cycle error rate and decode latency in 278 of the 280 evaluations. We release the full pipeline and the per-shot outcome of every evaluation, so future decoders and devices can be compared.

Runtime traces are becoming a central substrate for understanding agentic systems, yet interpretation has focused largely on what the agent did. Workplace agents face the complementary problem: interpreting the human activity that surrounds them. Hours of low-level events carry rich evidence about a user's state but are too granular to reason over directly, and flattening them into one stream or compressing them into a single embedding both treat "summarize the user's behavior" as if it had one correct answer. We argue instead that behavioral interpretation is resolution-dependent: the same trace should admit multiple addressable interpretations at different temporal resolutions. We construct a multi-resolution vocabulary of semantically normalized operators, recurring motifs, coherent episodes, and day-level rhythms, each preserving the structure salient at its own horizon. Applied to 667 million human-attributed events from a large commercial productivity suite (50,000 users, 100 organizations), it yields 120 operator types, thousands of motifs, 25 episode types, and five day-rhythm archetypes. We validate it on real telemetry: re-running the entire pipeline on a disjoint 2,000-user sample recovers the same taxonomy (structural stability), and on held-out users the full representation forecasts a user's next episode more accurately than a flat-operator baseline, a 17% relative macro-F1 gain (predictive validity), so the abstractions preserve future-relevant information rather than merely describe it. A controlled resolution ablation then shows that no single level is optimal across questions: different agent-facing questions about the same trace are best answered at different resolutions. Behavioral trace interpretation for agents should therefore be multi-resolution and query-conditioned: an agent should access the temporal grain a question needs, not one universal summary.

Vision foundation models (VFMs) are valuable in data-scarce domains such as surgery, where a single pretrained backbone can provide rich representations for many downstream tasks. Yet the dominant self-supervised pretraining paradigm uses only RGB images, leaving readily available complementary signals, such as depth maps, unused. This is a particular missed opportunity in surgery, where natural-image VFMs transfer poorly while the scene geometry is rich and informative. With strong off-the-shelf models now able to produce pseudo-labeled dense depth for any image corpus, we hypothesize that such signals can be folded into pretraining to learn better representations. We present DART, an RGB-D pretraining recipe that builds on DINOv2 with a simple modification: a pixel-space depth reconstruction objective applied to masked iBOT patches, supervised by pseudo-labeled depth. Depth is used only during pretraining, so fine-tuning and inference remain RGB-only. We find that this pixel-level reconstruction head improves representation quality rather than disrupting it. We further show that depth, which encodes scene geometry, is more effective as a target than alternative dense signals such as Canny edges, confirming that the gains stem from depth rather than added supervision alone. Across eight surgical benchmarks spanning segmentation, depth estimation, and image-level recognition, DART outperforms both natural-image and in-domain baselines, including a vanilla DINOv2 trained on identical data, improving dense prediction while also strengthening image-level understanding. More broadly, DART shows that freely available geometric pseudo-labels can strengthen foundation model pretraining without extra labels or added inference cost, pointing toward stronger backbones for surgery.

Unattended interactive autonomy - machines that step into danger in place of humans and complete tasks with human tools - remains a missing capability in mission-critical operations. These domains offer scarce training data and only onboard compute, yet deployed systems must face novelty without erasing prior competence. We introduce Continual Field-Adaptive Models (CFAMs), which learn efficiently in the lab and continue learning after deployment through autonomous, gradient-free, on-device updates. CFAM uses a complementary learning architecture with a frozen slow-learning component and a fast-learning Capsule Field. The slow component contains three cortices: Sensor, which maps multimodal input into 3D-grounded geometry; Reasoning, which decomposes tasks into skills and evaluates outcomes; and Action, which executes geometric skills. The Capsule Field stores field learning one-shot and gradient-free as Competence Capsules. Skill installation is few-shot in the lab and continual in the field; open-world novelty is outside scope. We evaluate CFAM across five embodiments: manipulator, quadruped, humanoid, quadrotor, and off-road vehicle. Baselines (pi0, CogACT, SpatialVLA) use the same in-house multi-embodiment dataset for physical-platform comparisons. CFAM reaches the operating point of a standard policy trained on the full prior-training dataset using 40% of the data, or 2.5x fewer trajectories. At test time, autonomous capture of verified near-OOD cases improves action success by 13.9 percentage points. In sequential simulation, backward transfer is -0.5 percentage points versus -11.4 for LoRA. CFAM therefore provides a bounded form of post-deployment physical intelligence: few-shot skill learning, autonomous field growth from verified near-OOD experience, and retention of prior competence.

Video-language benchmarks are usually constructed by the dataset authors without published reliability statistics, leaving the noise floor of the construct unknown. We argue that multimodal benchmarking benefits from methods taken from research communities that have already invested in strategies to ensure reliability. We illustrate the case with the Classroom Observation Protocol for Undergraduate STEM (COPUS): a 24-code multi-label observation instrument with a decade of peer-reviewed reliability literature. We recast COPUS as a video benchmark for multimodal foundation models, where it provides a dense set of structured labels (a 24-dimensional binary vector every 2 minutes across a 50-90 minute lecture), an externally validated vocabulary, and established literature that provides a per-code reliability target based on human evaluators. Annotations in our evaluation corpus are produced by a 5-person human-evaluator panel whose consensus matrix is our reference. We propose VISTA, a baseline that runs MiniCPM-V-4.5 over a dense sliding window, refines its per-window outputs with a lightweight multi-layer perceptron (MLP) head trained on top of the frozen backbone, and max-pools the resulting predictions onto the 2-minute COPUS grid. On three held-out chemistry lectures, VISTA reaches 80.1% restricted macro accuracy versus 74.9% for the zero-shot variant, with the largest residual errors on visually similar instructor codes and on rare audio-dependent codes. We characterize three systematic failure modes (audio-partial observability, fine-grained group-work discrimination, long-tail recall) and release the benchmark tooling, prompts and baseline code at https://github.com/ajfranck/VISTA.

We present AgentiGrid, an agentic artificial intelligence (AI) framework that integrates large language models (LLMs) intelligence and high-performance computing (HPC) to streamline and accelerate the multi-scenario power flow studies. AgentiGrid is an autonomous decision-making agent that proposes parameter modifications, invokes analyses through HPC analysis toolkit ExaGO, interprets results, and determines subsequent actions. ExaGO provides multiple power flow applications that can perform deterministic, stochastic and security constrained optimal power flow analyses. AgentiGrid provides backends to multiple LLMs (OpenAI, Anthropic, Ollama, and Ollama cloud) augmented with context specific and task specific prompts. Key features include interactive mid-search steering, goal-type-aware post-search analysis, and concurrent variant exploration for power flow optimization. A Streamlit-based graphical launcher provides real-time visualization of iteration progress and generates reports in natural language. AgentiGrid is capable of autonomously converging transmission constrained alternating current optimal power flow in under 20 iterations, with near-perfect reliability

We introduce Mitra-v2, a tabular foundation model that delivers state-of-the-art performance on real-world classification and regression problems, from credit-risk scoring and clinical prediction to equipment-failure detection and house-price estimation. Mitra-v2 is trained only on synthetic data, with a pretraining distribution that is much larger and more diverse than Mitra-v1's. Built on a small 2D Transformer backbone, Mitra-v2 supports longer contexts and larger feature spaces. Improved optimization lets it learn from this larger task distribution. We evaluate Mitra-v2 on the TabArena and TALENT benchmarks, comprising more than 300 real-world datasets under two evaluation protocols. On the full TabArena benchmark, Mitra-v2 delivers state-of-the-art performance at the level of the industry-scale TabFM and EXAONE Tabular models, while surpassing TabPFN-3 by a wide margin in both classification and regression. Mitra-v2 matches the 1.6B-parameter TabFM with only 5% of its size (77M parameters), delivering frontier performance at a fraction of the cost. On TALENT, Mitra-v2 remains among the leading models, clearly outperforming TabPFN-3 and TabICLv2. It also ranks first on classification tasks with more than ten classes, even though it was pretrained only on tasks with at most ten classes. These results make Mitra-v2 one of the strongest and most broadly applicable open tabular foundation models released to date. We release the model weights, the inference and fine-tuning code, and our evaluation results under the Apache-2.0 license.

Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language models replace token-level seriality with a long trajectory of iterative refinement. In this work, we introduce PlaidQ, a 0.7B continuous diffusion language model for code generation, and show that its trajectory can be aggressively distilled into only a few denoising steps---or even one, enabling efficient code generation. PlaidQ repurposes a pretrained autoregressive model as a bidirectional denoiser over continuous token embeddings. We distill PlaidQ with distribution matching for few-step generation and paired-trajectory supervision for one-step generation. At matched model scale, PlaidQ is competitive with discrete diffusion language models on code generation. Distillation then shifts the quality--compute frontier: a 16-step student reaches 31.78 and 40.49 pass@10 on HumanEval and MBPP+, surpassing the same PlaidQ teacher sampled for 512 steps. At the extreme, paired-trajectory distillation achieves 7.07 pass@1 on HumanEval with a single denoising step, producing functionally correct programs. Together, these results establish continuous diffusion as a viable path to few-step and one-step code generation. Broadly, continuous diffusion is not merely another representation for language: it provides an interface through which language models can inherit the acceleration and distillation machinery of continuous diffusion modeling. Training and inference code and model checkpoints are available at https://github.com/pengzhangzhi/plaidq.

Latent entity extraction (LEE) tackles the challenge of identifying implicit, contextually inferred entities within free text-an area where traditional entity extraction methods fall short. In this paper, we introduce LentEx, a novel framework for latent entity extraction that leverages synthetic data generation and instruction fine-tuning to optimize smaller, efficient large language models (LLMs). Latent entities, which are often abstract and thematic, are crucial for applications such as retrieval-augmented generation (RAG), customer persona analysis, and knowledge graph enrichment. LentEx addresses the scarcity of labeled datasets by employing a template-based approach to generate diverse, contextually rich synthetic data, ensuring high variability and alignment with real-world distributions. To our knowledge, LentEx is the first to systematically approach LEE through the lens of LLMs. LentEx demonstrates significant performance improvements across multiple tasks, notably surpassing state-of-the-art models on the MTEB Clustering Benchmark. Furthermore, our methodology enables robust generalization to unseen domains, making LentEx highly applicable in real-world NLP tasks, including RAG and clustering, thereby establishing a new paradigm for latent entity understanding and extraction in natural language processing.

We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this formulation, we introduce an agentic attacker with a dedicated search harness that performs environment reconnaissance, structured reasoning over attack strategies, and adaptive evaluation using victim-agent feedback. Across heterogeneous tasks, we find that increasing attacker test-time compute improves vulnerability discovery and exploitation, while ablations show that explicit strategy management is important for avoiding redundant search and sustaining gains at larger budgets. These results suggest that agentic security evaluations should characterize both the attacker's search procedure and compute budget, rather than treating attack success as a budget-independent property of the victim. More broadly, our findings identify the attacker's adaptive search over the system attack surfaces as an important and underexplored security risk for tool-using agents.

We present Hakken, a domain-agnostic prediction and explanation system performing knowledge prediction, i.e., growing scientific knowledge by establishing novel relationships, ones that are not limited to the deductive hull of previous knowledge. Hakken uses a transformer-based prediction model built on temporal sequences of knowledge graphs extracted from vast bodies of research publications, fused with an LLM's semantic knowledge, to predict the presence and define the type of as-yet undocumented relationships between scientific concepts. It then calls a model-agnostic explanation framework to provide accompanying information for each prediction that allows scientists to evaluate the suggested new relationship. While general purpose, we demonstrate Hakken's practical capabilities by applying it to the biomedical domain. There, Hakken's prediction model establishes a new benchmark for time-aware multi-label relation prediction, and we show that the model's output stays coherent and informative over extended time spans in historic data. In addition, we scored 1.5 million above-confidence-threshold hypotheses related to aging, qualitatively validated batches of these predictions with biologists and progressed three of them for empirical validation in wet-lab. Two predictions with potentially significant impact in the context of drug discovery and repurposing were confirmed, introducing previously undocumented interactions between TP53 and BAMBI, and between RAF1 and TNF, to biomedical science.

Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurrent-state write-back to denote this rule and isolate its effect in a compact GRU encoder--decoder for fluorescence lifetime imaging, a molecular imaging modality used in quantitative biological imaging. A central task is estimating two lifetime parameters, the short-lived component τ1 and the long-lived component τ2, from high-noise time-resolved fluorescence signals. Holding the trained model fixed, replacing continuous state propagation with deterministic 4-bit state storage increases estimation errors for τ1 and τ2 by approximately 70x and 300x, respectively. Failure occurs when repeated small updates remain below the write threshold, leaving the stored state nearly fixed while the network continues to propose change. Error feedback, residual memory, and direction memory carry information from these suppressed updates across time and recover accuracy without retraining. Precision sweeps show that increasing state precision can worsen a fixed recurrent solution, while matched training shows that compatibility with the state interface can be learned. To test whether this behavior extends beyond the GRU, we repeat the post-training intervention in an independently trained LSTM, where coarse write-back reproduces the failure, error feedback restores accuracy, and state-specific interventions reveal greater sensitivity of the cell state than the hidden state. Our results establish recurrent-state write-back as a key determinant of low-precision recurrent dynamics and identify the state-storage interface as a central design consideration for quantized recurrent inference.

Effective use of battery storage depends on reliable estimation of its state of health (SOH) and state of charge (SOC). Model-based state estimation requires the open-circuit voltage (OCV) curve, which is typically unknown for second-life batteries. We present a framework that jointly estimates the states and parameters of an equivalent circuit model solely from field operation data, using Gaussian process regression to reconstruct the OCV curve. Applied to a real second-life battery system of 27 modules and 324 cells, it reveals SOH heterogeneity, a systematic SOC imbalance, and two faulty cells, all validated against a reference measurement. We aggregate the cell SOH and SOC to module level and benchmark them against a lumped-module model fitted without the individual cell voltages. The lumped-module model follows the average behavior and cannot capture the limiting cells, overestimating SOH by up to 31% and SOC by up to 23%.