每日自动抓取：arXiv 当日新论文、近半年高被引论文、Hacker News 热门。仅供学习参考。

arXiv 今日新论文（AI / 机器学习 / 量化金融）

1. Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Bingxin Xu, Yuzhang Shang, Zhen Dong 等 · 2026-09-17

Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific …

2. Embedding Models Measure in Peculiar Ways
Juri Opitz, Andrianos Michail 等 · 2026-09-17

Embedding spaces define notions of semantic similarity and distance. We study whether those embeddings reflect physical measurements of mass, distance, time and volume, which admit a unique, objective notion of semantic …

3. Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Nitish Dashora, Douglas Chen, Idan Shenfeld 等 · 2026-09-17

Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many …

4. FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Kevin Qu, Tao Sun, Massimiliano Viola 等 · 2026-09-17

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation …

5. Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Ji Xie, Dewei Zhou, Xinyu Huang 等 · 2026-09-17

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and …

6. ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
Zahra Ghaffari, Massih Bahar, Mojgan Forootan 等 · 2026-09-17

Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of these syndromes are …

7. Quantifying Overclaiming Propensity in Frontier LLM Agents
Nolan Smyth, Yorguin-Jose Mantilla-Ramos, Pascal Jr Tikeng Notsawo 等 · 2026-09-17

Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify the propensity of frontier agents to …

8. Unifying Models of Intergroup Hostility in Online Discourse
Patrick Gerard, Julia Mendelsohn, Kristina Lerman 等 · 2026-09-17

Hostile rhetoric toward social groups can normalize exclusion and justify mistreatment, as well as contribute to rising polarization and political violence. Efforts to moderate hostile rhetoric in online speech draw on …

9. An Empirical Study of Harness Design for Coding Agents
Run-Ze Fan, Zihao Zhang, Simin Ma 等 · 2026-09-17

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the …

10. JEPA-Anything: Learning Predictive Models across Different Worlds
Taoyong Cui, Zhongyao Wang, Xinyue Xu 等 · 2026-09-17

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling …

11. RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Yan Yu, Zhengxi Lu, Yizhou Liu 等 · 2026-09-17

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher …

12. Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Sarah Wyer, Sue Black, Noura Al Moubayed 等 · 2026-09-17

Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit …

13. GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
Xin Chen, Sen Chen, Yujuan Ding 等 · 2026-09-17

Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different task stages may …

14. Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights
Tica Lin, Deepak Chandran, Gauri Jagatap 等 · 2026-09-17

Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequently difficult for a viewer to verify …

15. Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Sho Kawano, Zehang Richard Li, Paul A. Parker 等 · 2026-09-17

Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests …

共 15 篇。

近半年高被引论文

AI / 机器学习方向

量化金融方向

Hacker News 热门（科技 / 创业 / 投资风向）

本日报由服务器每日自动抓取生成于凌晨，原文链接均已附在上。