@inproceedings{zhang-etal-2026-temporal-gains, title = "Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models", author = "Zhang, Linghao and Li, Jungang and Hei, Yonghua and Tao, Sicheng and Dai, Song and Yan, Yibo and Dongfang, Zihao and Liu, Weiting and Qin, Chenxi and Li, Hanqian and Zou, Xin and Zhang, Jiahao and Xun, ShuHang and Jiang, Haiyun and Hu, Xuming", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.114/", pages = "2662--2679", ISBN = "979-8-89176-459-0" }