Embodied AI TopConf · ICCV2025

Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding

ICCV2025 / Vision-Language-Action Model

VLA视频感知
新标签打开 AlphaXiv新标签打开 Project
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding figure
AlphaXiv 中文论文页面（可滚动查看）