@inproceedings{tang-etal-2025-sparkle, title = "Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning", author = "Tang, Yihong and Qu, Ao and Wang, Zhaokai and Zhuang, Dingyi and Wu, Zhaofeng and Ma, Wei and Wang, Shenhao and Zheng, Yunhan and Zhao, Zhan and Zhao, Jinhua", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.findings-emnlp.217/", pages = "4083--4103", ISBN = "979-8-89176-335-7" }