@inproceedings{zhang-etal-2024-efficient,
    title = "Efficient Sparse Attention needs Adaptive Token Release",
    author = "Zhang, Chaoran  and
      Zou, Lixin  and
      Luo, Dan  and
      Luo, Xiangyang  and
      Li, Zihao  and
      Tang, Min  and
      Li, Chenliang",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-acl.837/",
    doi = "10.18653/v1/2024.findings-acl.837",
    pages = "14081--14094"
}