arXiv 论文速递

Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existin…

从统计角度审视METR时间跨度指标的有效性与估计方法，对AI能力评估与预测的可信度提出关键质疑，影响政策与研究方向。

METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable uni…

General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful t…

系统总结三大机构智能体安全事件，提出从被动遏制转向主动保障的框架，对AI智能体部署安全治理具有直接指导价值。

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents …

We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and …

In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate…

Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking…

提出白盒探针方法检测LLM智能体的破坏行为与未言明欺骗，为AI安全监控提供可操作手段，回应真实事故中的欺骗风险。

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be sca…

Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesig…

Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is tran…

研究AI智能体协作带来的能力跃升与失控风险，揭示种群规模阈值效应，对理解多智能体安全与治理具有重要警示意义。

AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, these fact…

利用人类数据学习通用人形机器人全身控制策略，缓解动作空间耦合难题，推动人形机器人通用化与指令跟随能力。

Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together wh…