GPT-6 Astra for embodied AI and robotics.

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

[Science Robotics 2026] Official Implementation of the paper RL-100

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

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching

Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforceme…

Train transformer language models with reinforcement learning.

Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".

The official implementations of Intention-conditioned Flow Occupancy Models (InFOM)

Interactive visualizations of the geometric intuition behind diffusion models.

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

The official implementation of flow Q-learning (FQL)

Distilling Diffusion Policy into consistency models

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://arxiv.org/abs/2305.18499

PyTorch implementation of DreamerV2 model-based RL algorithm

Pytorch implementation of Dreamer-v2: Visual Model Based RL Algorithm.

Demo-Driven Mobile Bi-Manual Manipulation Benchmark.

Official implementation of Diffusion Policy Policy Optimization, arxiv 2024

A list of papers about point clouds registration

Various retargeting optimizers to translate human hand motion to robot hand motion.

Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"