@inproceedings{chen-etal-2025-cost,
    title = "Cost-Optimal Grouped-Query Attention for Long-Context Modeling",
    author = "Chen, Yingfa  and
      Wu, Yutong  and
      Song, Chenyang  and
      Thai, Zhen Leng  and
      Shen, Xingyu  and
      Han, Xu  and
      Liu, Zhiyuan  and
      Sun, Maosong",
    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.272/",
    pages = "5360--5376",
    ISBN = "979-8-89176-332-6"
}