Act with Intent：为 VLA 模型蒸馏行为意图

Original title: Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

Source: arXiv cs.RO·2026-08-25 12:00Publish time unverified

arXiv:2608.23478v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction.