visuotactile benchmark for the deformable object manipulation

Companion code for the global workspace interpretability paper

Infinite Worlds with Versatile Interactions

RoboDojo Official Repo

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Galaxea's open-source VLA repository

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

符合nature论文学术表达和科研绘图的Skill

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

A Simple Baseline for Video World Models with Memory

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

MultiModal Audio Generation in Raw Waveform Space.

用Agent skills打造我的论文流水线

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

[NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Project Lyra: Open Generative 3D World Models

RoboClaw is an Embodied AI Assistant.

Isaac Gym environments and training for DexHand

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

WorldEngine: Towards the Era of Post-Training for Autonomous Driving

BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx