@inproceedings{liu-etal-2026-alloc,
    title = "Alloc-{M}o{E}: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference",
    author = "Liu, Baihui  and
      Tian, Kaiyuan  and
      Wang, Wei  and
      Zhang, Zhaoning  and
      Qiao, Linbo  and
      Li, Dongsheng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.437/",
    pages = "9653--9667",
    ISBN = "979-8-89176-390-6"
}