@inproceedings{xu-etal-2026-citycube,
    title = "{C}ity{C}ube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments",
    author = "Xu, Haotian  and
      Hu, Yue  and
      Zhu, Zhengqiu  and
      Gao, Chen  and
      Wang, Ziyou  and
      Rao, Junreng  and
      Lu, Wenhao  and
      Li, Weishi  and
      Yin, Quanjun  and
      Li, Yong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.416/",
    pages = "9190--9215",
    ISBN = "979-8-89176-390-6"
}