@inproceedings{pham-etal-2025-silvar,
    title = "{S}il{V}ar: Speech-Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization",
    author = "Pham, Tan-Hanh  and
      Nam, Le Hoang  and
      Nguyen, Phu-Vinh  and
      Ngo, Chris  and
      Hy, Truong-Son",
    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://aclanthology.org/2025.emnlp-main.589/",
    pages = "11674--11685",
    ISBN = "979-8-89176-332-6"
}