@inproceedings{song-etal-2026-anchoring,
    title = "Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning",
    author = "Song, Xinxin  and
      Li, Siyuan  and
      Xiao, Tingxiong  and
      Suo, Jinli",
    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.1051/",
    pages = "24131--24147",
    ISBN = "979-8-89176-459-0"
}