@article{250510917,
  title = {VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization},
  author = {Mingxiao Li and Na Su and Fang Qu and Zhizhou Zhong and Ziyang Chen and Yuan Li and Zhaopeng Tu and Xiaolong Li},
  year = {2025},
  eprint = {2505.10917},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.10917v2},
}