@inproceedings{li-etal-2026-crochetbench, title = "{C}rochet{B}ench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?", author = "Li, Peiyu and Huang, Xiaobao and Hua, Ting and Chawla, Nitesh V", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.604/", pages = "13229--13251", ISBN = "979-8-89176-390-6" }