DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

作者：Chenyang Li, Jieyuan Liu, Bin Li, Bo Gao, Yilin Yuan, Yangfan He, Yuchen Li, Jingqun Tang · 单位：Australian National University, University of California, San Diego, Chinese Academy of Sciences, Beijing Institute of Graphic Communication, University of North Carolina at Chapel Hill, Baidu Search, Bytedance · 会议/期刊：arXiv · 日期：2026-01-22 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning