Views
No views yet
ckpts.pt# TODO💡 MADFormer supports flexible AR↔Diff trade-offs. On FFHQ-1024, increasing AR layer allocation yields up to 75% FID improvements under low NFE settings.
1@misc{chen2025madformermixedautoregressivediffusion,
2 title={MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation},
3 author={Junhao Chen and Yulia Tsvetkov and Xiaochuang Han},
4 year={2025},
5 eprint={2506.07999},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2506.07999},
9}