@inproceedings{ou-etal-2026-mllms,
    title = "Do {MLLM}s Really See It: Reinforcing Visual Attention in Multimodal {LLM}s",
    author = "Ou, Siqu  and
      Wan, Tianrui  and
      Zhao, Zhiyuan  and
      Gao, Junyu  and
      Li, Xuelong",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.434/",
    pages = "9981--9997",
    ISBN = "979-8-89176-459-0"
}