A Survey of Reinforcement Learning for Large Reasoning Models

2026年1月更新，目前国内可用Docker镜像源汇总，DockerHub国内镜像加速列表，🚀DockerHub镜像加速器

北京邮电大学生存指南，从沙河到本部，从入学到毕业的全程陪伴

Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Fogsight is an AI agent and animation engine powered by Large Language Models.

Official implementation of “Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models” (AAAI 2026).

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Official implementation of Visco-Attack (EMNLP 2025 Main). We will progressively release the code and one-click reproduction scripts.

The source code of our paper: 'DecIF: Improving Instruction-Following through Decomposition'

Official repository of "CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement".

Skin changer for League of Legends (LOL)

Skin changer for League of Legends (LOL)

吴彦组的编译原理大作业

公交车调度