Lists (8)
Stars
[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos
WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild
PyTorch code and models for V-JEPA self-supervised learning from video.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
[CVPR 2026] HandX: Scaling Bimanual Motion and Interaction Generation
Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").
PyTorch code and models for VJEPA2 self-supervised learning from video.
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Vercel's official collection of agent skills
GigaWorld-0: World Models as Data Engine to Empower Embodied AI
EgoVerse: Egocentric Data for Robot Learning from Around the World
Lets make video diffusion practical!
Memory-Dependent Manipulation Benchmark based on RoboTwin
Enjoy the magic of Diffusion models!
HaMeR: Reconstructing Hands in 3D with Transformers
AI agents running research on single-GPU nanochat training automatically
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
Official code of Motus: A Unified Latent Action World Model
Distributed, scalable benchmarking of generalist robot policies.
A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
[CVPR 2026] UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos
Wan: Open and Advanced Large-Scale Video Generative Models
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI