@inproceedings{zhang-wang-2026-cityvg, title = "{C}ity{VG}: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3{D} Visual Grounding", author = "Zhang, Jianjun and Wang, Hanli", 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://aclanthology.org/2026.acl-long.1617/", doi = "10.18653/v1/2026.acl-long.1617", pages = "35012--35031", ISBN = "979-8-89176-390-6" }