Stars
Train your Agent model via our easy and efficient framework
Official Repository of Absolute Zero Reasoner
Collect the awesome works evolved around reasoning models like O1/R1 in visual domain
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
Recipes to train reward model for RLHF.
RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
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。
Fully open reproduction of DeepSeek-R1
✨✨Latest Advances on Multimodal Large Language Models
Latest Advances on Embodied Multimodal LLMs (or Vison-Language-Action Models).
[TMLR 2025🔥] A survey for the autoregressive models in vision.
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
🧑🚀 全世界最好的LLM资料总结（语音视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Align Anything: Training All-modality Model with Feedback
[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation
Official implementation of Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model (ICLR 2025 Oral)
llama3 implementation one matrix multiplication at a time
我的 ComfyUI 工作流合集 | My ComfyUI workflows collection
Accepted as [NeurIPS 2024] Spotlight Presentation Paper
Character Animation (AnimateAnyone, Face Reenactment)
Schedule-Free Optimization in PyTorch
Open-Sora: Democratizing Efficient Video Production for All
learning materials for PyTorch beginners
Pytorch Implementation of FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing (ICLR 2024)
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。