@inproceedings{wu-etal-2024-mobilevlm,
    title = "{M}obile{VLM}: A Vision-Language Model for Better Intra- and Inter-{UI} Understanding",
    author = "Wu, Qinzhuo  and
      Xu, Weikai  and
      Liu, Wei  and
      Tan, Tao  and
      Liujianfeng, Liujian  and
      Li, Ang  and
      Luan, Jian  and
      Wang, Bin  and
      Shang, Shuo",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2024.findings-emnlp.599/",
    doi = "10.18653/v1/2024.findings-emnlp.599",
    pages = "10231--10251"
}