SOURCE-LINKED INTELLIGENCE

DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

World Action Models (WAMs) jointly generate robot actions and predict future world states, transferring priors from video pretraining to robot control. However, future visual prediction is computationally expensive, so existing WAMs often rely on long action chunks to amortize inference cost across control steps, at the cost of closed-loop responsiveness. We present \method, a dual-system WAM that preserves broader-horizon world-action generation while enabling high-frequency closed-loop action updates by decoupling global planning and local refinement. \systwo periodically performs high-noise

Read original source ↗ Open in workspace

recordType

paper

region

Global