SOURCE-LINKED INTELLIGENCE

WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Humanoid whole-body manipulation requires coordinated whole-body dynamics, yet large-scale trajectories from a target robot are expensive to collect and difficult to scale. In contrast, whole-body motion from human and humanoid sources is abundantly available, although such data cannot be directly used as embodiment-specific robot actions. This work asks whether these scalable motion resources can instead provide a transferable predictive prior for humanoid world-action modeling. We introduce WholeBodyWAM, a humanoid world-action model that learns whole-body dynamics from large-scale heterogen

Read original source ↗ Open in workspace

recordType

paper

region

Global