arXiv 论文速递

将维基百科游戏作为超大规模文档检索基准，检验语言模型在无法索引场景下的导航与信息检索能力，推动检索增强方法发展。

Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic o…

Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-und…

The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological expressivity refers to a family of measures particularly …

揭示能力评估的根本漏洞：模型可证明地隐藏任意能力，使部署前的安全评估可能失效，对AI安全治理具有重大警示意义。

Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show…

A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a schedule $U$ drawn afresh for each output, we compare…

Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundle Protocol enables store-carry…

Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state mispercepti…

提出用自然语言直接设计蛋白质结构，突破传统设计模型需精确规格输入的局限，为de novo蛋白质设计提供更灵活可控的新范式。

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input r…

While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied de…

给出异步Q-learning单轨迹末迭代的击中时间界，推进了无同步假设下强化学习收敛理论的严格分析，具重要理论价值。

We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose sta…

指出同一注意力头在不同任务中角色不同，超越静态共享头识别，深化对大模型组件功能动态性的理解，助力可解释性与模型编辑。

Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of in…

As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availa…