Embodied AI TopConf · CORL2025

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models

CORL2025 / Vision-Language-Action Model

VLA感知
新标签打开 AlphaXiv
Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models figure
AlphaXiv 中文论文页面（可滚动查看）