AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration
AirGroundBench: 异构多视角具身协作下多模态大模型的空间智能探测
机构 * Beijing University of Posts and Telecommunications(北京邮电大学) ; QiYuanLab(启元实验室) ; Tsinghua University(清华大学) ; University of Electronic Science and Technology of China(电子科技大学)
专题命中 空间理解 :spatial understanding(abstract);分类 cs.CV
AI总结 提出AirGroundBench基准,通过异构无人机-无人车协作的多视角任务(10类、约6.2万道视觉问答和115个导航任务),系统评估多模态大模型在空间感知、跨视角对齐、空间变换推理和具身决策中的几何一致性,发现模型在跨视角对齐和变换推理上存在瓶颈。