A feature-rich command-line audio/video downloader

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Deepfakes Software For All

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

High-Resolution Image Synthesis with Latent Diffusion Models

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

Open-Sora: Democratizing Efficient Video Production for All

A generative world for general-purpose robotics & embodied AI learning.

Fully open reproduction of DeepSeek-R1

Image-to-Image Translation in PyTorch

Stable Diffusion with Core ML on Apple Silicon

Train transformer language models with reinforcement learning.

Lets make video diffusion practical!

verl: Volcano Engine Reinforcement Learning for LLMs

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

An open-source tool-augmented conversational language model from Fudan University

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

A collaboration friendly studio for NeRFs

🍦 Never use print() to debug again.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Minimal PyTorch implementation of YOLOv3

Point cloud diffusion for 3D model synthesis

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).