1
LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination
应对场景遮挡新方案，看视角想象如何提升VLA模型表现
arXiv:2606.10862v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, …