Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

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.

Building General-Purpose Robots Based on Embodied Foundation Model

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

Official code of Motus: A Unified Latent Action World Model

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

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

[RSS 2026] Causal video-action world model for generalist robot control

Official repository for OmniVLA training and inference code

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

A Pragmatic VLA Foundation Model

Unified, efficient, and easy-to-use inference infrastructure for edge AI || 面向端侧 AI 的统一、高效、易用的推理基础设施

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

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

The Overleaf LaTeX template of the bupt graduate thesis.

Open & Reproducible Research for Tracking VLAs

Official implementation of Any2Track.

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

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

FlashInfer: Kernel Library for LLM Serving

Structured state space sequence models

Integration of SLAM and autonomous navigation on the Unitree-Go2 robot.

Unitree Go2 simulation platform for testing navigation, decision-making and autonomous tasks. (NVIDIA Isaac/ROS2)

Roboto_origin Fully Open-Source DIY Humanoid Robot/萝博头原型机全开源手搓级人形机器人