@inproceedings{zhang2025beingvl05,
  title={Unified Multimodal Understanding via Byte-Pair Visual Encoding},
  author={Zhang, Wanpeng and Feng, Yicheng and Luo, Hao and Li, Yijiang and Yue, Zihao and Zheng, Sipeng and Lu, Zongqing},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2025}
}