VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs

作者：Haoran Yuan, Weigang Yi, Zhenyu Zhang, Wendi Chen, Yuchen Mo, Jiashi Yin, Xinzhuo Li, Xiangyu Zeng, Chuan Wen, Cewu Lu, Katherine Driggs-Campbell, Ismini Lourentzou · 单位：University of Illinois Urbana-Champaign, Stanford University, Shanghai Jiao Tong University · 会议/期刊：arXiv · 日期：2026-03-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Tactile-based Action Models / Prediction