Awesome Robotics Manipulation · full_paper

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

arXiv · 2026-02-04 · Low-Level Learning-Based Action Modelling / Input Modelling / Vision Action Models / Image-Action Models

Vision-Action感知机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Viewpoint Matters: Dynamically Optimizing Viewpoints with Masked Autoencoder for Visual Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）