SOURCE-LINKED INTELLIGENCE

Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation. However, existing WAMs often utilize imagined futures with limited adaptation to evolving execution progress, potentially introducing distracting or unreliable predictive cues. This limitation arises from two empirically identified forms of non-uniformity in future utility: (i) at the inter-progress level, the utility of imagined futures varies across execution stages as control demands change; and (ii) at the intra-progress level, individual future latents exhi

Read original source ↗ Open in workspace

recordType

paper

region

Global