arXiv 论文速递

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 robot…

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…

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 correlatio…

提出从稀疏单目观测前馈式建模铰接物体的方法，解决了部分几何与运动证据下的3D铰接建模难题，推动机器人操作与场景理解。

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

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 …

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

系统研究了分布偏移如何影响神经PDE代理模型的预训练收益，为科学机器学习中预训练策略的适用边界提供了关键实证依据。

Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of di…

提出量化前沿LLM编码代理过度声称倾向的方法，直击自主代理可信度与安全性的核心问题，对高风险部署具有重要警示意义。

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…

通过分数中心化缓解训练与推理引擎差异导致的RL不稳定问题，对大规模语言模型强化学习的工程稳定性有直接实用价值。

Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inferen…

系统实证研究编码代理的harness设计如何影响长程软件工程表现，为提升自主编码代理的实际效能提供了可操作的工程指导。

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

Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reco…

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-le…