#policy

智能AI None

1小时真机RL微调成功率破95%！HIL-ResRL：即插即用的VLA“外挂”神器

1小时真机RL微调成功率破95%。HIL-ResRL：即插即用的VLA“外挂”神器 量子位的朋友们 2026-06-24 18:38:38 来源： 量子位 在具身智能的浪潮中，视觉-语言-动作（VLA）模型展现出了惊人的泛化能力。然而，当你

VLA HIL ResRL

2026-06-24 量子位的朋友们

智能AI None

QPILOTS：针对流量策略的高效测试时 Q 转向

14801v1 Announce Type: new Abstract: Flow-matching and diffusion policies are expressive action generators, but optimizi

the critic QPILOTS

2026-06-16 Yifan Ruan, Chenyang Cao, Andreas Burger, Ali Pesaranghader, Kaveh Kamali, Jaehong Kim, Nandita Vijaykumar, Alan Aspuru-Guzik, Igor Gilitschenski, Nicholas Rhinehart

智能AI None

代理人工智能控制评估中的攻击选择会显着降低安全性

06529v1 Announce Type: new Abstract: An attacker that strategically chooses when to attack is much harder to catch than

attack safety and

2026-06-08 Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad IV, Joachim Schaeffer, Ram Potham, Tyler Tracy

智能AI None

OpenAI 公共政策议程

OpenAI outlines its public policy agenda for AI, including safety, youth protection, workforce transition, and global st

OpenAI outlines its

2026-06-07 OpenAI博客

智能AI None

行为诱导的 Mirror-Prox 时间差异学习可实现更快的离策略预测

arXiv:2605.28849v1 Announce Type: new Abstract: Gradient temporal-difference methods provide stable off-policy predictio

the metric behavior

2026-05-29 Xingguo Chen, Yuchen Shen, Shangdong Yang, Chao Li, Guang Yang, Wenhao Wang

智能AI None

AgentWall：本地 AI 代理的运行时安全层

16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open pr

and the agents

2026-05-20 Ashwin Aravind

开源推荐 None

GitHub 热门项目：GRPO-Zero

GitHub项目：GRPO-Zero 仓库地址：https://github。

the policy gradient

2026-05-18 GitHub Trending

开发者生态 None

自我蒸馏实现持续学习 [PDF]

Computer Science > Machine Learning arXiv:2601。

learning Learning arXiv

2026-05-17 teleforce

开发者生态 None

Rust 编译器的 LLM 政策

rust-lang / rust-forge Public Notifications You must be signed in to change notification settings Fork 233 Star 538 Conv

the rust this

2026-05-15 liyanage

智能AI None

学习何时采取行动：通过运行时保证进行高效沟通的强化学习

12561v1 Announce Type: new Abstract: Safe reinforcement learning (RL) typically asks $\textit{what}$ an agent should do。

and the Lyapunov

2026-05-14 Adam Haroon, Erick J. Rodr\'iguez-Seda, Cody Fleming, Tristan Schuler

智能AI None

政策蒸馏的多面性：陷阱、机制和修复

arXiv:2605.11182v1 Announce Type: new Abstract: On-policy distillation (OPD) and on-policy self-distillation (OPSD) have

and OPSD policy

2026-05-13 Siqi Zhu, Xuyan Ye, Hongyu Lu, Weiye Shi, Ge Liu

智能AI None

了解具有可解释性的注释器安全策略

05329v1 Announce Type: new Abstract: Safety policies define what constitutes safe and unsafe AI outputs, guiding data an

and annotators policy

2026-05-09 Alex Oesterling, Donghao Ren, Yannick Assogba, Dominik Moritz, Sunnie S. Y. Kim, Leon Gatys, Fred Hohman

数码硬件 None

正则化中心强调时间差异学习

04100v1 Announce Type: new Abstract: Off-policy temporal-difference (TD) learning with function approximation faces a st

the and policy

2026-05-08 Xingguo Chen, Chaohui Wu, Jinguo Ye, Chao Li, Shangdong Yang, Guang Yang, Tianyu Liang, Wenhao Wang