@article{mmotmixtureofmodalitytokenstransformer,
  title = {MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis},
  author = {Jianbin Zheng and Daqing Liu and Chaoyue Wang and Minghui Hu and Zuopeng Yang and Changxing Ding and DaCheng Tao},
  year = {2023},
  eprint = {2305.05992},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.05992v1},
}