GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation

Source: arXiv cs.RO·2026-09-04 12:00Publish time unverified

arXiv:2609.04193v1 Announce Type: new Abstract: Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and visual-prediction objectives may omit critical physical and task structure while retaining control-irrelevant visual redundancy. We call this mismatch between visual richness and control utility the action-sufficiency gap.