SOURCE-LINKED INTELLIGENCE

PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce \method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement. \method first retains a local fixed-offset JEPA objective and adds trajecto

Read original source ↗ Open in workspace

recordType

paper

region

Global