Highlights
- Pro
Stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
🌎💪 BrowserGym, a Gym environment for web task automation
SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.
Agent Skill Induction: "Inducing Programmatic Skills for Agentic Tasks"
2026 AI/ML internship & new graduate job list updated daily
AI-powered desktop companion to boost your efficiency
The absolute trainer to light up AI agents.
A repo for open research on building large reasoning models
[AI4MATH@ICML2025] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
[EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs
Chrome extension for clipping arXiv articles to Notion.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Official Repository of "Learning to Reason under Off-Policy Guidance"
[NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling
Minimal reproduction of DeepSeek R1-Zero
🔥 How to efficiently and effectively compress the CoTs or directly generate concise CoTs during inference while maintaining the reasoning performance is an important topic!
Tongji Univ. Undergraduate Graduation Project 2021. | 🎉含: 同济er毕设答辩PPT模板
🏡 GitHub Pages template for personal academic homepage
Building a comprehensive and handy list of papers for GUI agents
Overseas Summer Research Guidance 海外暑研申请指南
[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents
(已支持sqlsugar).NetCore、.Net6、Vue2、Vue3、Vite、TypeScript、Element plus+uniapp前后端分离，全自动生成代码；支持移动端(ios/android/h5/微信小程序。http://www.volcore.xyz/
The model, data and code for the visual GUI Agent SeeClick
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Fine-tune LLM agents with online reinforcement learning