@article{showoonesingletransformertounify,
  title = {Show-o: One Single Transformer to Unify Multimodal Understanding and Generation},
  author = {Jinheng Xie and Weijia Mao and Zechen Bai and David Junhao Zhang and WeiHao Wang and Kevin Qinghong Lin and YuChao Gu and Zhijie Chen and Zhenheng Yang and Mike Zheng Shou},
  year = {2024},
  eprint = {2408.12528},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.12528v6},
}