@inproceedings{liu-etal-2026-vida, title = "{VIDA}: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification", author = "Liu, Yanshan and Zhang, Hongbo and Sun, Zhen and Wei, Jiaheng and Wu, Kaishun", 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/corrections-2026-06/2026.findings-acl.1687/", doi = "10.18653/v1/2026.findings-acl.1687", pages = "33793--33804", ISBN = "979-8-89176-395-1" }