@misc{dl2-14-1,
  title={Neural Discrete Representation Learning},
  author={Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu},
  year={2017},
  url={https://arxiv.org/abs/1711.00937v2}
}
@misc{dl2-14-2,
  title={Taming Transformers for High-Resolution Image Synthesis},
  author={Patrick Esser, Robin Rombach, Björn Ommer},
  year={2021},
  url={https://arxiv.org/abs/2012.09841v3}
}
@misc{dl2-14-3,
  title={Finite Scalar Quantization: VQ-VAE Made Simple},
  author={Fabian Mentzer, David Minnen, Eirikur Agustsson, Michael Tschannen},
  year={2023},
  url={https://arxiv.org/abs/2309.15505v2}
}
@misc{dl2-14-4,
  title={Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation},
  author={Lijun Yu, José Lezama, Nitesh B. Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Vighnesh Birodkar, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A. Ross, Lu Jiang},
  year={2024},
  url={https://arxiv.org/abs/2310.05737v3}
}
@misc{dl2-14-5,
  title={An Image is Worth 32 Tokens for Reconstruction and Generation},
  author={Qihang Yu, Mark Weber, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen},
  year={2024},
  url={https://arxiv.org/abs/2406.07550}
}
@misc{dl2-14-6,
  title={Autoregressive Image Generation using Residual Quantization},
  author={Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, Wook-Shin Han},
  year={2022},
  url={https://arxiv.org/abs/2203.01941v2}
}