arXiv 论文速递

Flow policies have become a standard policy class for learning robot behaviors from demonstrations, but reinforcement learning is still critical for improving pre-trained flow poli…

Conformal prediction is a popular tool for uncertainty quantification that outputs prediction sets with finite-sample coverage guarantees. While prediction set size is commonly use…

用流匹配实现前馈式4D手物交互重建，避免昂贵的逐序列优化，对具身感知与交互建模有直接价值。

Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, …

训练LLM从相关文献中综合出研究想法，将文献理解与科研创意生成结合，对AI辅助科研有推动作用。

Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this…

为机器人操作构建3D世界模型，替代传统仿真器，可用于策略评估与改进，是机器人学习与数据驱动仿真的重要进展。

World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depe…

Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to t…

Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously…

针对网页代理的提示注入攻击，提出自适应世界模型训练方法，直击代理安全这一关键且紧迫的问题。

Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The…

We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equation with a spatially varying anti-diffusion coefficient. For constant coefficients, t…

解决自改进策略中固定评判器失效的问题，实现可扩展验证，对具身推理的持续自我提升至关重要。

Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedba…

Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models po…

Petri nets have been used to describe chemical processes such as reactions.They map well to chemistry: Places are the bonds between atoms and the free valence of each atom, a token…