@inproceedings{shen-etal-2025-zoomeye,
    title = "{Z}oom{E}ye: Enhancing Multimodal {LLM}s with Human-Like Zooming Capabilities through Tree-Based Image Exploration",
    author = "Shen, Haozhan  and
      Zhao, Kangjia  and
      Zhao, Tiancheng  and
      Xu, Ruochen  and
      Zhang, Zilun  and
      Zhu, Mingwei  and
      Yin, Jianwei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.335/",
    pages = "6613--6629",
    ISBN = "979-8-89176-332-6"
}