OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models
Published in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Highlight, 2026
OddGridBench is a controllable benchmark for evaluating fine-grained visual discrepancy sensitivity in multimodal large language models. The project page is available at wwwtttjjj.github.io/OddGridBench.
Recommended citation: Weng, Tengjin, Wenhao Jiang, Jingyi Wang, Ming Li, Lin Ma, and Zhong Ming. (2026). "OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Highlight.
Download Paper