技术雷达TECH RADAR · GITHUB · ARXIV · HACKER NEWS

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own

Jeremy Qin, David Schmotz, Derck Prinzhorn

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low

Jiabin Qiu, Zixuan Chen, Hongye Cao

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal stru

Sudip Bhujel, Shanghao Shi, Ruiquan Huang

Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, sa

Lior Biton, Oren Tsur

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrati

Yuyao Liu, Jiayuan Mao, David Hsu

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs

Yinghua Zhou, Junjie Ye, Yiqi Zhao

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic con

Matteo Merler, Bowen Li, Josh Roy

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can v

Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computat

Kimia Hamidieh, Giannis Daras, Antonio Torralba

Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEveryt

Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论