@inproceedings{chen-etal-2026-token,
    title = "Token-level Inference-Time Alignment for Vision-Language Models",
    author = "Chen, Kejia  and
      Zheng, Junjun  and
      Zhang, Jiawen  and
      Lin, Manxi  and
      Pan, Xiao  and
      Hu, Jiacong  and
      Lou, Jian  and
      Feng, Zunlei  and
      Song, Mingli",
    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.1253/",
    pages = "25012--25029",
    ISBN = "979-8-89176-395-1"
}