作者位次 #6/8IROS 2026Poster· Architectural Advances in Vision-Language-Action Models
ISF-VLA: An Implicit 3D Vision-Language-Action Model Capitalizing on 3D-Aware Vision Foundation Models through Implicit Spatial Fusion
Sheng Zang · Songlin Wei · Haoran Geng · Yikai Tang · Bo An · J. Senthilnath · Pieter Abbeel · Jitendra Malik
可解释性多模态Deep Learning in Grasping and ManipulationImitation LearningRepresentation LearningOpenReview