@inproceedings{shen-etal-2024-pruning,
    title = "Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations",
    author = "Shen, Bowen  and
      Lin, Zheng  and
      Zha, Daren  and
      Liu, Wei  and
      Luan, Jian  and
      Wang, Bin  and
      Wang, Weiping",
    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/add-emnlp-2024-awards/2024.findings-acl.582/",
    doi = "10.18653/v1/2024.findings-acl.582",
    pages = "9781--9793"
}