Core Python Controller of the ORCA Hand

An open-source implementation of Multitask Diffusion Transformer (DiT) Policy for robot manipulation as seen on Boston Dynamics Atlas Humanoid and in "A Careful Examination of Large Behavior Models…

Differentiable simulation for system identification and visuomotor control

EgoVerse: Egocentric Data for Robot Learning from Around the World

One framework to evaluate any VLA model on any robot simulation benchmark.

Train a Unitree G1 humanoid to perform a double spin kick using mjlab

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

Identify and simulate extended friction models for servo-actuators

Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/

K-Bot model inference

Actuator and IMU firmware stack

A repository for controlling actuators

Python firmware

KOS implementation for K-Bot

Simulation backend for KOS

A general-purpose, configurable framework for robot firmware

Motor flasher repository

The robot firmware

MuJoCo simulation code

A unified inference and post-training framework for accelerated video generation.

Goal is to solve sample efficiency by using ARC-AGI as a benchmark

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

v0 of Asimov, an open-source humanoid robot

Unofficial implementation of the Dreamer 4 world model in PyTorch.

PyTorch code and models for VJEPA2 self-supervised learning from video.

From the Transistor to the Web Browser, a rough outline for a 12 week course