arXiv 论文速递

指出跨信任边界自主协作的智能体社会需要社会性约束框架，为多智能体系统的安全协调与治理提供了基础性思路。

An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. W…

提出可递归自我改进的交互式科研智能体工作台，探索AI自主加速科学发现这一关键方向，对科研范式变革具有潜在深远影响。

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. Scienc…

Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods …

针对大模型在事实支撑薄弱时仍流畅作答的问题，提出自提问链实现选择性弃答与风险控制，对提升LLM可靠性至关重要。

Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answ…

Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame ra…

Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer…

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where t…

Unauthorized hardware replacement can preserve a wireless device's logical identity while altering its physical implementation, posing a challenge to hardware integrity verificatio…

基于既有缩放定律推出结构化数据通用智能模型LimiX-2，推动表格等结构化数据的通用建模能力，应用面广。

We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mec…

揭示同构与异构异步优化之间的桥接远比预期困难，对大规模分布式训练的理论理解与算法设计有重要警示意义。

Modern large-scale machine learning tasks often require multiple workers, devices, CPUs, or GPUs to compute stochastic gradients in parallel and asynchronously to train model weigh…

Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthe…

The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns. Here we examine the effect of bias in centered binary patterns under the Krotov-Ho…