Awesome Robotics Manipulation · full_paper

VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference

arXiv · 2025-11-20 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning

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 Code
VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference figure
AlphaXiv 中文论文页面（可滚动查看）