Embodied AI TopConf · ICML2025

SAM2Act:Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

ICML2025 / Policies

其他
新标签打开 AlphaXiv
SAM2Act:Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）