Awesome Robotics Manipulation · full_paper

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

CVPR 2026 · 2025-11-24 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies

VLA感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention figure
AlphaXiv 中文论文页面（可滚动查看）