VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models

作者：Jintao Cheng, Haozhe Wang, Weibin Li, Gang Wang, Yipu Zhang, Xiaoyu Tang, Jin Wu, Xieyuanli Chen, Yunhui Liu, Wei Zhang · 单位：The Hong Kong University of Science and Technology, The Chinese University of Hong Kong, South China Normal University, National University of Defense Technology, University of Science and Technology Beijing · 会议/期刊：arXiv · 日期：2026-03-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning