@inproceedings{tao2025hovle,
      title={HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding},
      author={Tao, Chenxin and Su, Shiqian and Zhu, Xizhou and Zhang, Chenyu and Chen, Zhe and Liu, Jiawen and Wang, Wenhai and Lu, Lewei and Huang, Gao and Qiao, Yu and Dai, Jifeng},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      pages={14559--14569},
      year={2025}
}