@article{towardsvisualtextgroundingofmultimodal,
  title = {Towards Visual Text Grounding of Multimodal Large Language Model},
  author = {Ming Li and Ruiyi Zhang and Jian Chen and Jiuxiang Gu and Yufan Zhou and Franck Dernoncourt and Wanrong Zhu and Tianyi Zhou and Tong Sun},
  year = {2025},
  eprint = {2504.04974},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.04974v1},
}