ICLR2025
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Fei Wang, Xingyu Fu, James Y. Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon, Muhao Chen
2025Year
Abstract
Figure 1: The MUIRBENCH Benchmark. MUIRBENCH contains 11,264 images and 2,600 multiplechoice questions, providing robust evaluation on 12 multi-image understanding tasks. Each example comes from one task in MUIRBENCH, presenting diverse multi-image relations.
