@inproceedings{fan-etal-2024-read,
    title = "Read Anywhere Pointed: Layout-aware {GUI} Screen Reading with Tree-of-Lens Grounding",
    author = "Fan, Yue  and
      Ding, Lei  and
      Kuo, Ching-Chen  and
      Jiang, Shan  and
      Zhao, Yang  and
      Guan, Xinze  and
      Yang, Jie  and
      Zhang, Yi  and
      Wang, Xin Eric",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.533/",
    doi = "10.18653/v1/2024.emnlp-main.533",
    pages = "9503--9522"
}