arXiv 论文速递

As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where we left something or what was…

揭示RLVR中探索与优化纠缠的核心矛盾，提出解耦方法，对提升大模型可验证奖励强化学习的效果与稳定性具有重要意义。

Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning …

解决机器人实时控制中视觉历史与动作延迟的矛盾，扩展世界-动作模型上下文，对长时序机器人操作有重要价值。

Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework…

为重尾噪声下去中心化SGD建立最优收敛率并阐明梯度裁剪作用，填补分布式优化理论空白，指导鲁棒训练。

Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and normalization. While these methods are well underst…

发现VLA模型对指令措辞高度敏感且未继承语言鲁棒性，提出缓解方法，对提升具身智能指令泛化能力关键。

Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on. A …

GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wis…

Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearnin…

针对机器人潜在世界模型缺乏规模化原则的问题，提出可扩展框架，对基于世界模型的机器人规划与控制意义重大。

Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their cap…

Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model…

Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed simil…

Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing va…

Online learning is an attractive framework in many domains because it permits well-defined learning even when data are dependent or chosen adversarially. This generality, however, …