@article{evaluatingcompositionalsceneunderstandin,
  title = {Evaluating Compositional Scene Understanding in Multimodal Generative Models},
  author = {Shuhao Fu and Andrew Jun Lee and Anna Wang and Ida Momennejad and Trevor Bihl and Hongjing Lu and Taylor W. Webb},
  year = {2025},
  eprint = {2503.23125},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.23125v1},
}