Stars
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
Lightweight coding agent that runs in your terminal
A curated list of papers and selected technical blogs on Loop Models.
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
[ArXiv 2026] Coevolving Representations in Joint Image-Feature Diffusion
Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency
Video-Action Models for Generalizable Robot Control Beyond VLAs
[RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model
Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
[ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…
Terrarium: Multi-turn data engine for evaluating and optimizing LLM agents in living environments.
Official code of Motus: A Unified Latent Action World Model
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
🦞 ClawMark: A Living-World Benchmark for Multi-Day, Multimodal Coworker Agents
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
HY-Embodied: Embodied Foundation Models for Real-World Agents
Elevate your AI research writing, no more tedious polishing ✨
科研写作助手 (Research Writing Assistant)
Gen-Searcher: Reinforcing Agentic Search for Image Generation
(ICCV 2025) "Principal Components" Enable A New Language of Images
[CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens