Stars
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
Harness engineering beginner tutorial, from 0 to 1
The agent that grows with you
给 Claude Code 装上完整联网能力的 skill：三层通道调度 + 浏览器 CDP + 并行分治
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening checklist.
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Tools for merging pretrained large language models.
这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。
Train transformer language models with reinforcement learning.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
My learning notes for ML SYS.
No fortress, purely open ground. OpenManus is Coming.
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
Simple introduction to LLM Agents
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Embark on the "Reinforcement Learning from Human Feedback" course and align Large Language Models (LLMs) with human values.
The official GitHub page for the survey paper "A Survey of Large Language Models".
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.