OrangeBot.AI Digest — 2026-01-20

The absolute trainer to light up AI agents.

Free, local, open-source Cowork for Gemini CLI, Claude Code, Codex, Opencode, Qwen Code, Goose Cli, Auggie, and more | 🌟 Star if you like it!

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Ultimate camera streaming application with support RTSP, RTMP, HTTP-FLV, WebRTC, MSE, HLS, MP4, MJPEG, HomeKit, FFmpeg, etc.

A curated list of awesome remote jobs and resources. Inspired by https://github.com/vinta/awesome-python

fresh directories for every vibe

Power full Task Manager

The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks predominantly evaluate code logic in static contexts, neglecting the dynamic, full-process requirements of real-world engineering, particularly in backend development which demands rigorous environment configuration and service deployment. To address this gap, we introduce ABC-Bench, a benchmark explicitly designed to evaluate agentic backend coding within a realistic, executable workflow. Using a scalable automated pipeline, we curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories. Distinct from previous evaluations, ABC-Bench require the agents to manage the entire development lifecycle from repository exploration to instantiating containerized services and pass the external end-to-end API tests. Our extensive evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks, highlighting a substantial disparity between current model capabilities and the demands of practical backend engineering. Our code is available at https://github.com/OpenMOSS/ABC-Bench.

Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT), but at the cost of long, low-bandwidth token sequences. Humans, by contrast, often reason softly by maintaining a distribution over plausible next steps. Motivated by this, we propose Multiplex Thinking, a stochastic soft reasoning mechanism that, at each thinking step, samples K candidate tokens and aggregates their embeddings into a single continuous multiplex token. This preserves the vocabulary embedding prior and the sampling dynamics of standard discrete generation, while inducing a tractable probability distribution over multiplex rollouts. Consequently, multiplex trajectories can be directly optimized with on-policy reinforcement learning (RL). Importantly, Multiplex Thinking is self-adaptive: when the model is confident, the multiplex token is nearly discrete and behaves like standard CoT; when it is uncertain, it compactly represents multiple plausible next steps without increasing sequence length. Across challenging math reasoning benchmarks, Multiplex Thinking consistently outperforms strong discrete CoT and RL baselines from Pass@1 through Pass@1024, while producing shorter sequences. The code and checkpoints are available at https://github.com/GMLR-Penn/Multiplex-Thinking.

Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over complex anatomical and volumetric structures. Here we present Medical SAM3, a foundation model for universal prompt-driven medical image segmentation, obtained by fully fine-tuning SAM3 on large-scale, heterogeneous 2D and 3D medical imaging datasets with paired segmentation masks and text prompts. Through a systematic analysis of vanilla SAM3, we observe that its performance degrades substantially on medical data, with its apparent competitiveness largely relying on strong geometric priors such as ground-truth-derived bounding boxes. These findings motivate full model adaptation beyond prompt engineering alone. By fine-tuning SAM3's model parameters on 33 datasets spanning 10 medical imaging modalities, Medical SAM3 acquires robust domain-specific representations while preserving prompt-driven flexibility. Extensive experiments across organs, imaging modalities, and dimensionalities demonstrate consistent and significant performance gains, particularly in challenging scenarios characterized by semantic ambiguity, complex morphology, and long-range 3D context. Our results establish Medical SAM3 as a universal, text-guided segmentation foundation model for medical imaging and highlight the importance of holistic model adaptation for achieving robust prompt-driven segmentation under severe domain shift. Code and model will be made available at https://github.com/AIM-Research-Lab/Medical-SAM3.

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance due to noisy retrieved contexts. Specifically, contradictory or irrelevant evidence tends to inflate the model's false certainty, leading to severe overconfidence. To address this, we propose NAACL Rules (Noise-AwAre Confidence CaLibration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design NAACL, a noise-aware calibration framework that synthesizes supervision from about 2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NAACL equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NAACL yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NAACL paves the way for both accurate and epistemically reliable LLMs.

Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-directional Preference Optimization (BiPO) shows that dense steering vectors can be learned directly from preference data in a Direct Preference Optimization (DPO) fashion, enabling control over truthfulness, hallucinations, and safety behaviors. However, dense steering vectors often entangle multiple latent factors due to neuron multi-semanticity, limiting their effectiveness and stability in fine-grained settings such as cultural alignment, where closely related values and behaviors (e.g., among Middle Eastern cultures) must be distinguished. In this paper, we propose Yet another Policy Optimization (YaPO), a reference-free method that learns sparse steering vectors in the latent space of a Sparse Autoencoder (SAE). By optimizing sparse codes, YaPO produces disentangled, interpretable, and efficient steering directions. Empirically, we show that YaPO converges faster, achieves stronger performance, and exhibits improved training stability compared to dense steering baselines. Beyond cultural alignment, YaPO generalizes to a range of alignment-related behaviors, including hallucination, wealth-seeking, jailbreak, and power-seeking. Importantly, YaPO preserves general knowledge, with no measurable degradation on MMLU. Overall, our results show that YaPO provides a general recipe for efficient, stable, and fine-grained alignment of LLMs, with broad applications to controllability and domain adaptation. The associated code and data are publicly availablehttps://github.com/MBZUAI-Paris/YaPO.

Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen 2.5 achieve significant gains even with spurious or incorrect rewards. We investigate this phenomenon and identify a "Perplexity Paradox": spurious RLVR triggers a divergence where answer-token perplexity drops while prompt-side coherence degrades, suggesting the model is bypassing reasoning in favor of memorization. Using Path Patching, Logit Lens, JSD analysis, and Neural Differential Equations, we uncover a hidden Anchor-Adapter circuit that facilitates this shortcut. We localize a Functional Anchor in the middle layers (L18-20) that triggers the retrieval of memorized solutions, followed by Structural Adapters in later layers (L21+) that transform representations to accommodate the shortcut signal. Finally, we demonstrate that scaling specific MLP keys within this circuit allows for bidirectional causal steering-artificially amplifying or suppressing contamination-driven performance. Our results provide a mechanistic roadmap for identifying and mitigating data contamination in RLVR-tuned models. Code is available at https://github.com/idwts/How-RLVR-Activates-Memorization-Shortcuts.

Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the space of model personas by extracting activation directions corresponding to diverse character archetypes. Across several different models, we find that the leading component of this persona space is an "Assistant Axis," which captures the extent to which a model is operating in its default Assistant mode. Steering towards the Assistant direction reinforces helpful and harmless behavior; steering away increases the model's tendency to identify as other entities. Moreover, steering away with more extreme values often induces a mystical, theatrical speaking style. We find this axis is also present in pre-trained models, where it primarily promotes helpful human archetypes like consultants and coaches and inhibits spiritual ones. Measuring deviations along the Assistant Axis predicts "persona drift," a phenomenon where models slip into exhibiting harmful or bizarre behaviors that are uncharacteristic of their typical persona. We find that persona drift is often driven by conversations demanding meta-reflection on the model's processes or featuring emotionally vulnerable users. We show that restricting activations to a fixed region along the Assistant Axis can stabilize model behavior in these scenarios -- and also in the face of adversarial persona-based jailbreaks. Our results suggest that post-training steers models toward a particular region of persona space but only loosely tethers them to it, motivating work on training and steering strategies that more deeply anchor models to a coherent persona.

Character image animation is gaining significant importance across various domains, driven by the demand for robust and flexible multi-subject rendering. While existing methods excel in single-person animation, they struggle to handle arbitrary subject counts, diverse character types, and spatial misalignment between the reference image and the driving poses. We attribute these limitations to an overly rigid spatial binding that forces strict pixel-wise alignment between the pose and reference, and an inability to consistently rebind motion to intended subjects. To address these challenges, we propose CoDance, a novel Unbind-Rebind framework that enables the animation of arbitrary subject counts, types, and spatial configurations conditioned on a single, potentially misaligned pose sequence. Specifically, the Unbind module employs a novel pose shift encoder to break the rigid spatial binding between the pose and the reference by introducing stochastic perturbations to both poses and their latent features, thereby compelling the model to learn a location-agnostic motion representation. To ensure precise control and subject association, we then devise a Rebind module, leveraging semantic guidance from text prompts and spatial guidance from subject masks to direct the learned motion to intended characters. Furthermore, to facilitate comprehensive evaluation, we introduce a new multi-subject CoDanceBench. Extensive experiments on CoDanceBench and existing datasets show that CoDance achieves SOTA performance, exhibiting remarkable generalization across diverse subjects and spatial layouts. The code and weights will be open-sourced.

PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision and released in a compact JSON schema with word-, line-, and paragraph-level bounding boxes. The corpus spans 209.5K articles (1.5M pages; ~1.3B words) and supports layout-aware modeling, coordinate-grounded QA, and evaluation of OCR-dependent pipelines. We analyze corpus characteristics (e.g., journal coverage and detected layout features) and discuss limitations, including reliance on a single OCR engine and heuristic line reconstruction. We release the data and schema to facilitate downstream research and invite extensions.

Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the "Fish-in-the-Ocean" (FITO) paradigm, which requires models to construct explicit cross-modal evidence chains within native scientific documents. To operationalize FITO, we build SIN-Data, a scientific interleaved corpus that preserves the native interleaving of text and figures. On top of it, we construct SIN-Bench with four progressive tasks covering evidence discovery (SIN-Find), hypothesis verification (SIN-Verify), grounded QA (SIN-QA), and evidence-anchored synthesis (SIN-Summary). We further introduce "No Evidence, No Score", scoring predictions when grounded to verifiable anchors and diagnosing evidence quality via matching, relevance, and logic. Experiments on eight MLLMs show that grounding is the primary bottleneck: Gemini-3-pro achieves the best average overall score (0.573), while GPT-5 attains the highest SIN-QA answer accuracy (0.767) but underperforms on evidence-aligned overall scores, exposing a gap between correctness and traceable support.

To teach robots complex manipulation tasks, it is now a common practice to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for long-term operation in the real world, where robots must continually adapt to new tasks and environments while retaining the knowledge they have already acquired. Existing continual learning methods for robotics commonly require storing previous data (exemplars), struggle with long task sequences, or rely on task identifiers for deployment. To address these limitations, we propose CLARE, a general, parameter-efficient framework for exemplar-free continual learning with VLAs. CLARE introduces lightweight modular adapters into selected feedforward layers and autonomously expands the model only where necessary when learning a new task, guided by layer-wise feature similarity. During deployment, an autoencoder-based routing mechanism dynamically activates the most relevant adapters without requiring task labels. Through extensive experiments on the LIBERO benchmark, we show that CLARE achieves high performance on new tasks without catastrophic forgetting of earlier tasks, significantly outperforming even exemplar-based methods. Code and data are available at https://tum-lsy.github.io/clare.

OzLabs 是一个澳大利亚自由软件开发者组织，该组织成员负责了很多知名的开源项目如 Samba、rsync、Linux PPP、Linux netfilter、Linux Advanced Power Management (APM) 和 OpenBMC。该组织成立于 1999 年，由 Linuxcare 聘请 Andrew Tridgell 负责组建。Linuxcare 在 2001 年的动荡导致大部分成员都离开了，他们加入了 IBM Linux Technology Center 从事 PowerPC Linux 及相关项目。但截至 2026 年 1 月，所有成员都离开了 IBM，结束了 OzLabs 与 IBM 长达 25 年的合作关系。

在流媒体和社交媒体的推荐算法时代，人们的注意力很少会被少数几部作品所捕获，曾经引领时代吸引无数人关注的好莱坞作品越来越少见了。1939 年的《乱世佳人》售出了 2 亿张电影票，而当时的美国人口仅为 1.3 亿。《陆军野战医院(M*A*S*H）》在 1983 年播出最后一集时吸引了逾一亿人观看。2025 年只有三部美国电影的票房收入超过 10 亿美元，而 2019 年这一数字为九部。YouTube 之所以能成为电视上最受欢迎的视频平台，不是因为它拥有最热门的节目，而是因为它能满足所有人需求。互联网打破了好莱坞对发行渠道的垄断。

Similarweb 最新数据显示，Threads 移动端日活用户数超越了 X。而 X 在 Web 端仍然远超 Threads，日访问量约 1.5 亿，而 Threads 的日访问量为 850 万。Similarweb 的数据显示，截至 2026 年 1 月 7 日 Threads 在 iOS 和 Android 平台上的日活用户数达到 1.415 亿，而 X 在移动设备上的日活用户数为 1.25 亿。Threads 日活增长受益于在 Meta 旗下社交平台如 Facebook 和 Instagram 上的推广，以及对内容创作者的重视和新功能的快速推出。Threads 过去一年新增了兴趣社区、完善筛选功能、私信、长文本、阅后即焚等功能，最近还在测试游戏功能。

英伟达除了供应 AI 芯片外，还开发了自己的大模型，如 NeMo、Retro-48B、InstructRetro 和 Megatron。那么这些大模型的训练数据来自何处？图书作者指控英伟达使用盗版书库训练模型。上周五原告修改了诉状，指控英伟达使用了影子图书馆“安娜的档案（Anna’s Archive）”收集的盗版电子书库。诉状援引英伟达内部邮件和文件称，英伟达员工主动联系“安娜的档案”，询问该影子图书馆提供的付费“高速访问”是什么意思。安娜的档案要求英伟达管理层内部批准之后它才会提供该服务。英伟达据报道在一周内批准了这一要求，安娜的档案随后提供了 500 TB 电子书的高速访问。英伟达还被控从 LibGen、Sci-Hub 和 Z-Library 下载书籍。

乐施会(Oxfam)发表年度报告《Resisting the Rule of the Rich》，称全球财富不平等在加速。2025 年亿万富翁的财富激增 2.5 万亿美元，几乎相当于全球半数人口（约 41 亿人）的财富总和。全球亿万富翁人数首次突破 3000 人，世界首富马斯克（Elon Musk）的财富也首次突破 5000 亿美元。报告警告，超级富豪正形成新的寡头政治，他们利用巨额财富收买政治、媒体和司法以维护自身财富，瓦解和摧毁进步政策，剥夺我们的基本公民权利和政治权利。报告举例说，贝佐斯收购《华盛顿邮报》，马斯克收购 Twitter/X，黄馨祥（Patrick Soon-Shion）控制《洛杉矶时报》，法国极右翼亿万富翁 Vincent Bollore 拥有 CNews。乐施会呼吁全世界人民联合起来捍卫自身权利，争取一个取代不平等和寡头政治的替代方案。

澳大利亚纽卡斯尔大学的研究人员发现，仅 10 分钟的高强度运动就能提高血液中几种小分子的水平。这些分子能够启动 DNA 修复机制，并关闭癌症生长信号。其中许多分子具有减轻炎症、维护血管健康和促进新陈代谢的作用。这些快速的变化似乎能够抑制肠道癌细胞的生长，同时还能加快受损DNA的修复速度。当科学家在实验室中将含有这些运动驱动分子的血液暴露于肠癌细胞时，他们观察到了广泛的基因变化——超过 1300 个基因的活动发生了改变，包括那些参与DNA修复、能量生产和癌细胞生长的基因。研究表明，运动通过血液发送分子信号，影响控制肿瘤生长和遗传稳定性的基因。这些结果进一步证明，保持身体活动是癌症预防的重要组成部分。研究团队发现，运动增加了支持线粒体能量代谢的基因活性，这有助于细胞更有效地利用氧气。与此同时，与快速细胞分裂相关的基因活性出现下调，可能使癌细胞侵袭性降低。运动后采集的血液还增强了DNA修复能力，激活了一个名为 PNKP 的关键修复基因。

社媒研究员通常需要与平台进行合作，但双方的利益关系很多时候并没有公开。近三分之一的社媒研究有着未披露的利益关联，部分研究员接受了社媒的资助，部分曾与社媒行业的员工合作发表过研究。研究人员认为，此类关联可能会扭曲研究结果。研究人员分析了《科学》、《自然》、PNAS 及其子刊如《Science Advances》和《Nature Communications》上的 295 篇社媒论文，它们的总引用次数有 5 万次，被逾 1.5 万篇新闻报道引用。其中五分之一的署名作者承认获得社媒企业的资助或有过合作。研究人员之后使用 OpenAlex 分析了署名作者和社媒企业之间的关联，发现一半作者存在关联，也就是有 30% 的作者没有披露潜在利益冲突。

根据 AI 工具平台 OpenRouter 和风险投资公司 a16z 的分析，2025 年 11 月中国企业开发的生成式 AI 占到了全球市场份额约 15%，相比 1 年前的 1% 大幅提升。性能测试显示，去年 12 月发布的 DeepSeek 模型在 92 个模型中排在第 9 位。作为开源模型排名第 1，其次是阿里巴巴的 Qwen（千问），它们在性能方面超过了 Google 和 OpenAI 的开源模型。日本企业开发 AI 时也在使用中国的 DeepSeek 和 Qwen。

根据最新报告，数据中心在 2026 年将消耗内存产量的最多七成。内存需求的指数级增长几乎肯定会冲击到汽车、电视和消费电子产品等众多行业。尽管汽车和消费电子产品等使用的是较老的内存类型，但内存制造商已经缩减或完全停产了旧内存芯片。报告称，2028 年的内存产能都售罄了，更别提今年了。几乎所有电子产品都需要内存，内存价格的暴涨将会导致本已经利润微薄的消费电子产品厂商将大部分上涨的成本转嫁给消费者——假如它们还有内存可用的话。IDC 更新了 2026 年的预测，预计智能手机销量将下滑 5%，PC 销量将下滑 9%——几个月后这些预测可能还会进一步调整。分析师表示这是有史以来内存行业最疯狂的时期。

根据 Cloudflare Rader 和 Netblocks 的监测，伊朗仍然处于基本断网状态，对互联网的封锁已进入第 12 天。在这此前，伊朗的流量有关短暂的恢复，但很快又时断时续，显示伊朗政府正在测试一个信息严格过滤的国内互联网。根据官方的数据，此前的大规模抗议导致了逾五千人死亡，逾两万人被捕。非官方数据认为死亡人数可能超过万人。

保时捷上周宣布，2025 年该公司在欧洲销售的汽车中电动版本销量超过了燃油版本。保时捷在欧洲销售的汽车插电版本占到了 57.9%。该公司最畅销的车型是 Macan，它有电动版本和燃油版本，在全世界的总销量为 84,328 辆，其中电动版本为 45,367 辆，占到了 53.8%。即使在美国市场，Macan 的电动版本占到总销量的三分之一。美国是唯一一个电动汽车销量下降的主要汽车市场，去年的电动汽车销量占到了总销量的大约 10%。

微软在 2026 年释出的首个 Windows 11 更新就被发现存在了多个严重问题，以至于它被迫释出紧急更新修复问题。紧急更新修复了多个 bug，包括 Windows 11 23H2 PC 无法正常关机；远程桌面 Remote Desktop 的登陆问题。微软还透露了其它问题，Outlook Classic 使用 POP 帐户时崩溃，该 bug 尚未修复；Windows 随机出现黑屏问题，桌面会冻结一两秒，屏幕变黑，然后恢复正常，该问题可能是更新本身或 GPU 驱动的兼容性问题导致的。

国家统计局公布了最新的人口统计数据。2025 年末全国人口 140489 万人，全年出生人口 792 万人、死亡人口 1131 万人，人口总量同比减少 339 万人。人口出生率 5.63‰，死亡率 8.04‰，自然增长率为 -2.41‰。从性别构成看，男性人口 71685 万人，女性人口 68804 万人，总人口性别比为 104.19。从年龄构成看，16—59 岁人口 85136 万人，占全国人口的比重为 60.6%；60 岁及以上人口 32338 万人，占全国人口的 23.0%，其中 65岁及以上人口 22365 万人，占全国人口的 15.9%。从城乡构成看，城镇常住人口 95380 万人，比上年末增加 1030 万人；乡村常住人口 45109 万人，减少 1369 万人；城镇人口占全国人口的比重为 67.89%。从受教育程度看，16—59 岁人口平均受教育年限达到 11.3 年 ，比上年提高 0.1年。

美国出生率下降对名校影响不大，但不那么知名的大学面临招不到足够的学生而不得不削减开支，解雇教职工，甚至关闭。自 2020 年以来，美国有逾 40 所大学宣布了关闭计划。Huron Consulting Group 预测，未来十年可能有约 400 所高校消失，约 60 万名学生受到影响，180 亿美元捐赠基金将重新分配。预计 2025 年后全美大学生生源数量将进一步减少。高校面临每届新生人数可能比上一届少的风险。财政压力将持续增加。2007 年美国出生人数创历史新高，之后出生率开始下降。面临招生困难的高校通常招国际学生去填补空缺，但特朗普去年重创了这一策略，他颁布了旅行禁令，放慢了签证申请流程，威胁驱逐外国学生维权者。结果是去年秋季全美国际学生入学人数减少了近 5000 人。

OpenAI 周五宣布未来几周测试为 ChatGPT 引入广告。这家估值 5000 亿美元的初创公司正在寻找新的收入来源以资助其持续扩张，以及与 Google 和 Anthropic 等竞争对手展开竞争。广告将先在美国进行测试，将出现在免费版本和 8 美元月费 ChatGPT Go 用户的答案的底部，仅在与用户所查询问题相关时展示。Pro、Business 和 Enterprise 订阅服务都不会有广告。OpenAI 预测 2026 年的广告收入将达到数十亿美元，未来几年会更高。