논문해외
Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs
HF Daily Papers
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety.
원문의 저작권은 HF Daily Papers에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.