Stars
ICRA2026: ABPolicy Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation
Real-Time VLAs via Future-state-aware Asynchronous Inference.
[NeurIPS 2025] LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation
An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.
A toolbox for real-to-sim reconstruction and robotic simulation
Official repo for GraspGen: A Diffusion-based Framework for 6-DOF Grasping
XenseRobotics Physical-Ai Intelligence Platform
Taccel: Scaling-up Vision-based Tactile Robotics with High-performance GPU Simulation
CVPR 2025(Highlight) DexGraspAnything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
Running VLA at 30Hz frame rate and 480Hz trajectory frequency
[ICLR 2025 Oral] Seer: Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
[AAAI 2026] Official code for MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
The official implement of VITA, VITA15, LongVITA, VITA-Audio, VITA-VLA, and VITA-E.
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
Scalable and user friendly neural 🧠 forecasting algorithms.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning
JAX implementation of WSRL and RL baselines | ICLR 2025
DelinQu / SimplerEnv-OpenVLA
Forked from simpler-env/SimplerEnvEvaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo, and OpenVLA) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)
EDM2 and Autoguidance -- Official PyTorch implementation
Tactile Sensing • IL/RL/VLA/WM • Manipulation • Representation • Simulation • Open Source
This repository includes code for Beyond Grip Force (BGF) paper
Project page of SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending