Embodied AI TopConf · ICLR2026

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning

ICLR2026 / Planning and Reasoning

规划/推理感知
新标签打开 AlphaXiv
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning figure
AlphaXiv 中文论文页面（可滚动查看）