@inproceedings{wang-etal-2026-bridging,
    title = "Bridging the Temporal Gap in Multimodal {LLM}s: Deeply Stacking Temporal Tokens for Audio-Visual Speech Recognition",
    author = "Wang, Liyong  and
      Xing, Junliang  and
      Hu, Tianyu  and
      Jiang, Jianfei  and
      Zhao, Jihuai  and
      Ma, Huimin",
    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://aclanthology.org/2026.findings-acl.1381/",
    doi = "10.18653/v1/2026.findings-acl.1381",
    pages = "27748--27759",
    ISBN = "979-8-89176-395-1"
}