Embodied AI TopConf · ICLR2026

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

ICLR2026 / Vision-Language-Action Models

视觉语言动作三维视觉感知
新标签打开 AlphaXiv
From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors figure
AlphaXiv 中文论文页面（可滚动查看）