@inproceedings{du-etal-2024-embspatial,
    title = "{E}mb{S}patial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models",
    author = "Du, Mengfei  and
      Wu, Binhao  and
      Li, Zejun  and
      Huang, Xuanjing  and
      Wei, Zhongyu",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-short.33/",
    doi = "10.18653/v1/2024.acl-short.33",
    pages = "346--355"
}