@inproceedings{zhang2025umu,
  title={Unified Multimodal Understanding via Byte-Pair Visual Encoding},
  author={Wanpeng Zhang and Yicheng Feng and Hao Luo and Yijiang Li and Zihao Yue and Sipeng Zheng and Zongqing Lu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2025}
}