نسخة أولية وصول مفتوح
LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks
Vision-language-action (VLA) models struggle to reuse recurring interactions in unseen tasks. Our diagnostic study reveals that reliable task completion does not imply consistent execution of constituent atomic actions across task contexts. We present LexiconVLA, a retrievable atomic-action lexicon for cross-task reuse …