@inproceedings{yao-etal-2026-edgeformer,
    title = "{E}dge{F}ormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks",
    author = "Yao, Yiming  and
      Niu, Jianwei  and
      Dai, Bin  and
      Ren, Tao",
    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.2007/",
    pages = "43346--43361",
    ISBN = "979-8-89176-390-6"
}