Article

How Representational Priors Shape Generalization in World Action Models

This study proposes that the generalization performance of world action models (WAMs) diverges significantly depending on the representational geometry of their generative backbones, and quantifies this prior using nuisance orthogonality (the degree to which features are orthogonal to the in-distribution manifold under out-of-distribution visual variations). Experiments across various image and video backbones find that higher orthogonality before training is associated with stronger robustness to visual variations after WAM training, enabling prospective prediction of policy generalization before training. Analysis of robust WAMs also reveals suppressed feature displacement and robust action generation.

Part of the event: Study finds backbone representation geometry determines world action model generalization

This page provides a summary and source link only.