@InProceedings{zhang2025beingvl05, author = {Zhang, Wanpeng and Feng, Yicheng and Luo, Hao and Li, Yijiang and Yue, Zihao and Zheng, Sipeng and Lu, Zongqing}, title = {Unified Multimodal Understanding via Byte-Pair Visual Encoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {12976-12986} }