Lists (8)
Starred repositories
[ICML 2026] 🏂 World Guidance: World Modeling in Condition Space for Action Generation
Source code for 👏🏻"CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos"
When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering (RSS 2026)
Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)
STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Official implementation of No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Official Implemenation for RAEv2: Improved Baselines with Representation Autoencoders
OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
Interactive World Model papers organized by core research challenges.
A platform for reproducible world model research and evaluation
MotuBrain: An Advanced World Action Model for Robot Control
37
Updated Jun 14, 2026
A Minimalist, Batteries-included Repository for Advancing World Model Science.
[ICML 2026] ResVLA: From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges
Code for "Predicting What Matters: Robust Generalist Robot Policy Learning via Future Semantic Mask".
A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.
Implementation for paper "Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models".
repository for training action-conditioned latent diffusion world models for robot video generation
Implementation of D4RT, Efficiently Reconstructing Dynamic Scenes, from Deepmind
[CVPR 2026] Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface