@inproceedings{wang-etal-2025-advancing,
    title = "Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models",
    author = "Wang, Wei  and
      Li, Zhaowei  and
      Xu, Qi  and
      Li, Linfeng  and
      Cai, YiQing  and
      Jiang, Botian  and
      Song, Hang  and
      Hu, Xingcan  and
      Wang, Pengyu  and
      Xiao, Li",
    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.721/",
    pages = "14282--14301",
    ISBN = "979-8-89176-332-6"
}