Article

GAWM: A Compact Latent World-Action Model for Multi-Task Robot Manipulation

The authors propose GAWM (Geometry-Aware World Model), a compact multi-task world-action model that predicts future observations in the latent space of a frozen DINOv3 encoder, with fewer than 100 million parameters and no robot or video pretraining.

Part of the event: GAWM Compact World-Action Model Paper Released

This page provides a summary and source link only.