@inproceedings{huang-etal-2026-nosa,
    title = "{NOSA}: Native and Offloadable Sparse Attention",
    author = "Huang, Yuxiang  and
      Wang, Pengjie  and
      Han, Jicheng  and
      Zhao, Weilin  and
      su, Zhou  and
      Sun, Ao  and
      Lyu, Hongya  and
      Zhao, Hengyu  and
      Wang, Yudong  and
      Xiao, Chaojun  and
      Han, Xu  and
      Liu, Zhiyuan",
    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.279/",
    pages = "6356--6381",
    ISBN = "979-8-89176-459-0"
}