Embodied AI TopConf · CVPR2025

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

CVPR2025 / Vision-Language-Action Models

视觉语言动作规划/推理感知
新标签打开 AlphaXiv
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）