@inproceedings{zhou-etal-2026-deputy,
    title = "Deputy: Accelerating Large Language Model Inference with Dynamic Low-Rank Substitution",
    author = "Zhou, Yuhua  and
      Weng, Shichao  and
      Zhou, Changhai  and
      Wu, Yuhan  and
      Qiao, Qian  and
      Gao, Jun  and
      Yang, Fei  and
      Pan, Aimin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.991/",
    pages = "19791--19810",
    ISBN = "979-8-89176-395-1"
}