TempoFit: Plug-and-Play Layer-Wise Temporal KV Memory for Long-Horizon Vision-Language-Action Manipulation

作者：Jun Sun, Boyu Yang, Jiahao Zhang, Ning Ma, Chencheng Wu, Siqing Zhang, Yiou Huang, Qiufeng Wang, Shan Liang, Yaran Chen · 单位：University · 会议/期刊：arXiv · 日期：2026-03-08 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies