@article{visionfoundationmodelsaseffectivevisual,
  title = {Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation},
  author = {Anlin Zheng and Xin Wen and Xuanyang Zhang and Chuofan Ma and Tiancai Wang and Gang Yu and Xiangyu Zhang and Xiaojuan Qi},
  year = {2025},
  eprint = {2507.08441},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.08441v1},
}