Awesome Robotics Manipulation · full_paper

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models

arXiv · 2026-03-30 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / PEFT

VLA感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper
FocusVLA: Focused Visual Utilization for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）