@inproceedings{zhao-etal-2026-hears,
    title = "It Hears, It Sees too: Multi-Modal {LLM} for Depression Detection By Integrating Visual Understanding into Audio Language Models",
    author = "Zhao, Xiangyu  and
      Shen, Yaling  and
      Jiang, Yiwen  and
      Wang, Zimu  and
      Liu, Jiahe  and
      Cheng, Maxmartwell H  and
      Oliveira, Guilherme C  and
      Desimone, Robert  and
      Dwyer, Dominic  and
      Ge, Zongyuan",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.211/",
    pages = "4185--4196",
    ISBN = "979-8-89176-444-6"
}