@inproceedings{gao-etal-2025-vision, title = "Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation", author = "Gao, Qiyue and Pi, Xinyu and Liu, Kevin and Chen, Junrong and Yang, Ruolan and Huang, Xinqi and Fang, Xinyu and Sun, Lu and Kishore, Gautham and Ai, Bo and Tao, Stone and Liu, Mengyang and Yang, Jiaxi and Lai, Chao-Jung and Jin, Chuanyang and Xiang, Jiannan and Huang, Benhao and Chen, Zeming and Danks, David and Su, Hao and Shu, Tianmin and Ma, Ziqiao and Qin, Lianhui and Hu, Zhiting", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1342/", pages = "26170--26195", ISBN = "979-8-89176-256-5" }