Can Vision-Language Models Solve Visual Math Equations?

We examine how counting, object recognition, and symbolic reasoning affect vision-language models when solving equations represented by images.

Recommended citation: Monjoy Narayan Choudhury*, Junling Wang*, Yifan Hou, Mrinmaya Sachan. (2025). "Can Vision-Language Models Solve Visual Math Equations?." Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). https://aclanthology.org/2025.emnlp-main.547/