QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models

作者：Yixuan Li · 单位：School of Artificial Intelligence, University of the Chinese Academy of, Institute of Automation, Chinese, Academy of Science, Technology Co · 会议/期刊：arXiv · 日期：2025-10-16 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models