@article{introducingvisualperceptiontokeninto,
  title = {Introducing Visual Perception Token into Multimodal Large Language Model},
  author = {Runpeng Yu and Xinyin Ma and Xinchao Wang},
  year = {2025},
  eprint = {2502.17425},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.17425v1},
}