Awesome Robotics Manipulation · full_paper

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

arXiv · 2025-10-16 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper
QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）