ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
Yuxuan Song, Zhe Zhang, Yu Pei, Jingjing Gong, Qiying Yu, Zheng Zhang, Mingxuan Wang, Hao Zhou
Abstract
Generative modeling of discrete variables is challenging yet crucial for applications in natural language processing and biological sequence design. We introduce the Shortlisting Model (SLM), a novel simplex-based diffusion model inspired by progressive candidate pruning. SLM operates on simplex centroids, reducing generation complexity and enhancing scalability. Additionally, SLM incorporates a flexible implementation of classifier-free guidance, enhancing unconditional generation performance. Extensive experiments on DNA promoter and enhancer design, protein design, character-level and large-vocabulary language modeling demonstrate the competitive performance and strong potential of SLM. Our code can be found at https://github.com/GenSI-THUAIR/SLM.
BibTeX
@inproceedings{
song2025shortlisting,
title={ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation},
author={Yuxuan Song and Zhe Zhang and Yu Pei and Jingjing Gong and Qiying Yu and Zheng Zhang and Mingxuan Wang and Hao Zhou and Jingjing Liu and Wei-Ying Ma},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=ZAu7sADxfh}
}