Stars
Being-H is BeingBeyond's family of human-centric embodied foundation models.
[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
One framework to evaluate any VLA model on any robot simulation benchmark.
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
Edit Banana: A framework for converting statistical formats into editable.
InternDataEngine: Pioneering High-Fidelity Synthetic Data Generator for Robotic Manipulation
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.
Helios: Real Real-Time Long Video Generation Model
Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer
首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
CVPR2025 | TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation
Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos"
Dexbotic: Open-Source Vision-Language-Action Toolbox