Embodied AI TopConf · ICCV2025

CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance

ICCV2025 / Vision-Language-Action Model

VLA感知
新标签打开 AlphaXiv
CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance figure
AlphaXiv 中文论文页面（可滚动查看）