BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

Tools for the Embody 3D Dataset

A lightweight suite of motion imitation methods for training controllers.

[SIGGRAPH Asia 2025] Implementation of "StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data"

Survey: A collection of AWESOME papers and resources on the latest research in Mixture of Experts.

TrackerLab is a cutting-edge modular framework for humanoid motion retargeting, trajectory tracking, and skill-level control, built on top of IsaacLab.

Versatile toolbox for humanoid robot control, featuring whole-body tracking, split strategies, and rapid experimentation across platforms. 🤖🌍

[ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

Implementation of Flow Policy Optimization (FPO)

Direct IsaacLab Workflow for Legged Robots

Code for "Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions" on unitree G1

Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills"

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

HOVER

The official codebase of paper "GMT: General Motion Tracking for Humanoid Whole-Body Control"

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Official Implementation of the CVPR 2024 highlight paper: Real-Time Simulated Avatar from Head-Mounted Sensors

Official implementation of NeurIPS 2024 paper: "Omnigrasp: Simulated Humanoid Grasping on Diverse Objects".

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

A Paper List for Humanoid Robot Learning.

Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

RL Extension Library for Robots, Based on IsaacLab.

 Now we have become very big, Different from the original idea. Collect premium software in various categories. With repository stars⭐ and forks🍴

The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

[CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions