EgoVerse: Egocentric Data for Robot Learning from Around the World

DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

Unofficial implementation of the Dreamer 4 world model in PyTorch.

AI agents running research on single-GPU nanochat training automatically

Best practices & guides on how to write distributed pytorch training code

Cosmos Policy

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

Open-Sora: Democratizing Efficient Video Production for All

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

robomimic: A Modular Framework for Robot Learning from Demonstration

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

A Paper List for Humanoid Robot Learning.

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

Official Repo for the paper "Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO" (TMLR 2026, AI4Math, MOSS @ ICML 2025).

Python inverse kinematics based on MuJoCo.

Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Deploy walk-these-ways project on Unitree Go2

Code for paper "Compositional Sculpting of Iterative Generative Processes"

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

open Multi-View Stereo reconstruction library

[CoRL25] GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

[CoRL 2024] RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation

Scene Graph API (C++ and Python)

Add-on for Blender, provides importing robots from URDF format