@inproceedings{zhang-etal-2026-minos, title = "Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text", author = "Zhang, Junzhe and Zhang, Huixuan and Hu, Xinyu and Lin, Li and Gao, Mingqi and Qiu, Shi and Wan, Xiaojun", 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.744/", pages = "15108--15132", ISBN = "979-8-89176-395-1" }