Han, S.; Fan, H.; Fu, J.; Li, L.; Li, T.; Cui, J.; Wang, Y.; Tai, Y.; Sun, J.; Guo, C.-L. EvalMuse-40K: A Fine-Grained Benchmark With Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation. AAAI 2026, 40, 4583-4591.