@inproceedings{xie-etal-2026-flexee,
    title = "{F}lex{EE}: Self-Speculative and {KV}-Compatible Early Exiting for Offloading-Aware {LLM} Inference",
    author = "Xie, Qihu  and
      Li, Ziwei  and
      Kang, Yi",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1426/",
    doi = "10.18653/2026.findings-emnlp.1426",
    pages = "30396--30411",
    ISBN = "979-8-89176-462-0"
}