Embodied AI TopConf · RSS2025

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

RSS2025 / General

视觉语言动作三维视觉
新标签打开 AlphaXiv
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model figure
AlphaXiv 中文论文页面（可滚动查看）