@inproceedings{chandhok-etal-2025-response, title = "Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities", author = "Chandhok, Shivam and Fan, Wan-Cyuan and Shwartz, Vered and Balasubramanian, Vineeth N. and Sigal, Leonid", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.acl-long.1241/", pages = "25530--25545", ISBN = "979-8-89176-251-0" }