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

@misc{liThu Oct 16 2025 16:11:18 GMT+0000 (Coordinated Universal Time)qdepthvlaquantizeddepth,
      title={QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models},
      author={Yixuan Li and Yuhui Chen and Mingcai Zhou and Haoran Li},
      year={Thu Oct 16 2025 16:11:18 GMT+0000 (Coordinated Universal Time)},
      eprint={2510.14836},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.14836},
}