High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Janus-Series: Unified Multimodal Understanding and Generation Models

Fully open reproduction of DeepSeek-R1

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

🙌 OpenHands: Code Less, Make More

Genesis Reinforcement Learning Environments

Distributed Robot Interaction Dataset.

✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Stay on top of trending topics on social media and the web with AI

Diffusion-LM

World's First Large-scale High-quality Robotic Manipulation Benchmark

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory

Make websites accessible for AI agents

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

FastVideo is a lightweight framework for accelerating large video diffusion models.

A series of technical report on Slow Thinking with LLM

Implementation of "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

Unofficial implementation of Meta's MovieGen models

[NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

VideoSys: An easy and efficient system for video generation

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Unifying 3D Mesh Generation with Language Models

[ICLR2025] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Parallel computing with task scheduling

A trainable PyTorch reproduction of AlphaFold 3.