@inproceedings{luo-etal-2026-lightmoe,
    title = "{L}ight{M}o{E}: Task-Aware Expert Availability Management for Memory-Efficient {M}o{E}-{LLM} Inference",
    author = "Luo, Puhan  and
      Yao, Yunhao  and
      Wang, Junyang  and
      Zhang, Junyang  and
      Li, Xiangyang",
    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.1062/",
    pages = "21124--21134",
    ISBN = "979-8-89176-395-1"
}