Embodied AI TopConf · ICML2026

HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning

ICML2026 / Vision-Language-Action Models

VLA规划/推理感知
新标签打开 AlphaXiv
HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning figure
AlphaXiv 中文论文页面（可滚动查看）