@article{optimizingvisionlanguageconsistencyviacr,
  title = {Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment},
  author = {Yifan Wang and Hongfeng Ai and Quangao Liu and Maowei Jiang and Ruiyuan Kang and Ruiqi Li and Jiahua Dong and Mengting Xiao and Cheng Jiang and Chenzhong Li},
  year = {2025},
  eprint = {2508.00945},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.00945},
}