@inproceedings{qiu-etal-2026-vlms, title = "Can {VLM}s Predict Future States? Bootstrapping World Models from Inverse Dynamics", author = "Qiu, Yifu and Ziser, Yftah and Korhonen, Anna and Cohen, Shay B and Ponti, Edoardo", 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.1772/", pages = "35579--35600", ISBN = "979-8-89176-395-1" }