@inproceedings{zhou-etal-2023-modular,
    title = "Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference",
    author = "Zhou, Wangchunshu  and
      Le Bras, Ronan  and
      Choi, Yejin",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-acl.664/",
    doi = "10.18653/v1/2023.findings-acl.664",
    pages = "10452--10465"
}