Embodied AI TopConf · ICLR2026

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

ICLR2026 / Vision-Language-Action Models

VLA3D 视觉感知
新标签打开 AlphaXiv
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model figure
AlphaXiv 中文论文页面（可滚动查看）