@inproceedings{he-etal-2026-pop,
    title = "{POP}: Prefill-Only Pruning for Efficient Large Model Inference",
    author = "He, Junhui  and
      Fu, Zhihui  and
      Wang, Jun  and
      Li, Qingan",
    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.291/",
    pages = "5864--5877",
    ISBN = "979-8-89176-395-1"
}