Home
Publications
Photo Gallery
Self-Evaluation Unlocks Any-Step Text-to-Image Generation
Xin Yu, Xiaojuan Qi, Zhengqi Li, Kai Zhang, Richard Zhang, Zhe Lin, Eli Shechtman, Tianyu Wang, Yotam Nitzan
CVPR · 2026 · Co-Lead
Xiaojuan Qi: Project lead; Tianyu Wang: Project lead; Yotam Nitzan: Project lead
Research summary
A from-scratch training approach for text-to-image generation that supports any-step inference using self-evaluation mechanism.
Key insight
Introduces a self-evaluation mechanism that enables high-quality text-to-image generation at any number of inference steps without a pretrained teacher, bridging the gap between fast few-step and high-quality many-step generation.
arXiv version linked; publication venue as listed above
Paper & resources
BibTeX
@article{yu2025selfe,
title={Self-Evaluation Unlocks Any-Step Text-to-Image Generation},
author={Yu, Xin and Qi, Xiaojuan and Li, Zhengqi and Zhang, Kai and Zhang, Richard and Lin, Zhe and Shechtman, Eli and Wang, Tianyu and Nitzan, Yotam},
journal={arXiv preprint arXiv:2512.22374},
year={2025}
}