Han, S. et al. 2026. EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 6 (Mar. 2026), 4583–4591. DOI:https://doi.org/10.1609/aaai.v40i6.42458.