From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

作者：Zhuofan Li, Hongkun Yang, Zhenyang Chen, Yangxuan Chen, Yingyan (Celine) Lin +, Chaojian Li + · 单位：Hong Kong University of Science and Technology, Georgia Institute of Technology · 会议/期刊：arXiv · 日期：2026-03-19 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Efficiency Analysis