Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
机构 * The University of Auckland(奥克兰大学) ; King Abdullah University of Science and Technology(国王 Abdullah 科学与技术大学) ; Tokyo University of Science(东京科学大学) ; RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心)
专题命中 VLA模型 :vision-language-action(title,abstract);action model(title);VLA(abstract);分类 cs.CV、cs.LG