ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models

作者：Wencheng Ye · 单位：School of Computer Science and, Technology, Tongji University, University of Technology Sydney, Advanced Institute of Big Data · 会议/期刊：arXiv · 日期：2025-11-22 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Small Model