@article{visionlanguagevisionautoencoderscalablek,
  title = {Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models},
  author = {Tiezheng Zhang and Yitong Li and Yu-cheng Chou and Jieneng Chen and Alan Yuille and Chen Wei and Junfei Xiao},
  year = {2025},
  eprint = {2507.07104},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.07104},
}