@inproceedings{zhu-etal-2025-foldmoe,
    title = "{F}old{M}o{E}: Efficient Long Sequence {M}o{E} Training via Attention-{M}o{E} Pipelining",
    author = "Zhu, Guichao  and
      Lei, Lintian  and
      Qing, Yuhao  and
      Fu, Yichao  and
      Li, Fanxin  and
      Huang, Dong  and
      Sun, Zekai  and
      Cui, Heming",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.186/",
    pages = "3705--3717",
    ISBN = "979-8-89176-251-0"
}