Concise CPU Incremental Potential Contact Simulation

Tactile Sensing • Simulation • Representation • Manipulation • RL/IL/VLA • Open Source

verl: Volcano Engine Reinforcement Learning for LLMs

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

The easiest, most secure way to use WireGuard and 2FA.

[PG2025] PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU

RL implementations

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Official code release for CoRL'25 paper: VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning

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

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

A fast and simple implementation of learning algorithms for robotics.

C5D: Sequential Continuous Convex Collision Detection Using Cone Casting

[CoRL 2025] Neural Robot Dynamics

Official Repository for NeurIPS 2025 Paper: Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

Vi-TacMan: Articulated Object Manipulation via Vision and Touch

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

Code Repository for ControlVLA, CoRL2025.

Official code of RDT 2

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulation

DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation

Reference PyTorch implementation and models for DINOv3

Python interface to the AgileX Piper arms, wrapping the piper_sdk.

Agilex College