@inproceedings{yin-etal-2025-sea,
    title = "{SEA}: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in {MLLM}s",
    author = "Yin, Yuanyang  and
      Zhao, Yaqi  and
      Zhang, Yajie  and
      Zhang, Yuanxing  and
      Lin, Ke  and
      Wang, Jiahao  and
      Tao, Xin  and
      Wan, Pengfei  and
      Zhang, Wentao  and
      Zhao, Feng",
    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/name-variant-enfa-fane/2025.emnlp-main.55/",
    doi = "10.18653/v1/2025.emnlp-main.55",
    pages = "1058--1070",
    ISBN = "979-8-89176-332-6"
}