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

A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

TuulAI RobotBuilder: Robotics Course to go from Zero to Hero in AI driven Robots

A general physic-based retargeting framework.

[Humanoids 2025 Oral] Universal Humanoid Robot Pose Learning from Internet Human Videos

Code for "PHUMA: Physically-Grounded Humanoid Locomotion Dataset"

A optimized PyTorch framework for behavior cloning with flow related generative models.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Official code of RDT 2

A lightweight suite of motion imitation methods for training controllers.

Official PyTorch implementation of the paper: Flow Matching in Latent Space

Real-time pose estimation accelerated with NVIDIA TensorRT

The implementation of elevation mapping on humanoid robots using a single MID-360 LiDAR.

[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning"

HoloMotion: A Foundation Model for Whole-Body Humanoid Control

Official Repository for MolmoAct

A collection of paper/projects that trains flow matching model/policies via RL.

Whole-Body Nonlinear MPC for Realtime Humanoid Loco-Manipulation Planning and Control

Unifying IsaacLab and Whole-Body Control in One Modular Framework

The definitive Web UI for local AI, with powerful features and easy setup.

RL-Boy Reinforcement Kid is a small-sized open-source robot project and a full-stack open-source scaled-down humanoid robot project.