Viewpoint Matters: Dynamically Optimizing Viewpoints with Masked Autoencoder for Visual Manipulation

作者：Pengfei Yi, Yifan Han, Junyan Li, Litao Liu, Wenzhao Lian · 单位：Rutgers University, School of Artificial Intelligence, Shanghai Jiao Tong University · 会议/期刊：arXiv · 日期：2026-02-04 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Vision Action Models / Image-Action Models