@article{revealingthegapinhumanandvlmscenepercept,
  title = {Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency},
  author = {Ziqi Wen and Parsa Madinei and Miguel P. Eckstein},
  year = {2026},
  eprint = {2605.13047},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.13047},
}