Stars
Agentic RAG R1 Framework via Reinforcement Learning
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
ThinkDepth.ai Deep Research
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。
This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners.
Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
Train your Agent model via our easy and efficient framework
Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling [ICCV 2025] Official PyTorch implementation
SkyRL: A Modular Full-stack RL Library for LLMs
Agent that converts natural language queries into SQL and provides response and query created
The latest research progress of Contrastive Learning(CL), Data Augmentation(DA) and Self-Supervised Learning(SSL) in Recommender Systems
Code for ICMR 2024 paper "BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval"
Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"
[ICCV 2025] This repo is the official implementation of "Music Grounding by Short Video"
This is the official code implementation for 《M2Beats 2.0: When Motion Meets Beats in Short-form Videos Twice》. More details will be released once the paper is published!
How can we build a true AI agent? Like Claude Code.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step