manifoldai-research/WorldScape-Policy

Official implementation of "Geometric Action Model for Robot Policy Learning"

Official code of UniWAM: Unified World-Action Model

REKI: a 2.4B vision-language-action model pretrained on public data only, with a memory of its recent past at negligible cost.

High-fidelity world models for general embodied intelligence, such as data engines and world simulators.

[ICML2026] VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Official Repository for MolmoAct2

What Enables In-Context Behavior Prompting for Manipulation?

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models