@inproceedings{wan-etal-2026-test, title = "Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning", author = "Wan, Cong and He, Ying and Huang, Zhongzhan and Wu, Hefeng", 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.383/", pages = "7751--7767", ISBN = "979-8-89176-395-1" }