Embodied AI TopConf · ICML2025

UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent

ICML2025 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent figure
AlphaXiv 中文论文页面（可滚动查看）