Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

[arXiv 2025] TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Dexbotic: Open-Source Vision-Language-Action Toolbox

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Benchmarking Knowledge Transfer in Lifelong Robot Learning

LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark

world modeling challenge for humanoid robots

This is a repository for reinforcement learning implementation for Unitree robots, based on IsaacLab.

[CoRL 2025] TWIST: Teleoperated Whole-Body Imitation System

RoboTwin 2.0 Offical Repo

Curated coding interview preparation materials for busy software engineers

Isaac Gym Environments for Legged Robots

Unified framework for robot learning built on NVIDIA Isaac Sim

[arXiv 2025] VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

[SIGGRAPH Asia 2025] Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A differentiable rasterizer used in the project "2D Gaussian Splatting"

Official implemetation of the paper "Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting".

[arXiv 2025] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.

Reference PyTorch implementation and models for DINOv3

Tutorial on how to get started with MuJoCo Simulation Platform. MuJoCo stands for Multi-Joint dynamics with Contact. It was acquired and made freely available by DeepMind in October 2021, and open …

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.