GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation
技术动态AI 85
来源：arXiv cs.RO发布时间待核实
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. We investigate whether this gap can be bridged by guiding intermediate …