@article{dovisionlanguagemodelstrulyperformvision,
  title = {Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap},
  author = {Yige Xu and Yongjie Wang and Zizhuo Wu and Kaisong Song and Jun Lin and Zhiqi Shen},
  year = {2026},
  eprint = {2604.16256},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.16256},
}