Starred repositories
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Official implementation of paper LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
A Minimalist, Batteries-included Repository for Advancing World Model Science.
Official implementation of AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models
Official implementation of "Latent Action Learning Requires Supervision in the Presence of Distractors", ICML 2025
[ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds. 面向游戏与虚拟世界的AI原生渲染引擎
EgoVerse: Egocentric Data for Robot Learning from Around the World
[ICML'26] Official implementation of "Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression"
[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions
[CVPR 2026] HandX: Scaling Bimanual Motion and Interaction Generation
AI agents running research on single-GPU nanochat training automatically
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight
GigaWorld-0: World Models as Data Engine to Empower Embodied AI
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx