Embodied AI TopConf · ICLR2026

Spatially Guided Training for Vision-Language-Action Model

ICLR2026 / Vision-Language-Action Models

视觉语言动作三维视觉感知
新标签打开 PDF新标签打开 Paper
Spatially Guided Training for Vision-Language-Action Model figure
在线论文 PDF（可滚动查看）