Embodied AI TopConf · CORL2025

3DS-VLA: A 3D Spatial-Aware Vision Language Action Model for Robust Multi-Task Manipulation

CORL2025 / Vision-Language-Action Model

视觉语言动作三维视觉感知
新标签打开 PDF新标签打开 Paper
3DS-VLA: A 3D Spatial-Aware Vision Language Action Model for Robust Multi-Task Manipulation figure
在线论文 PDF（可滚动查看）