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
@article{arxiv.2508.17345,
title = {ShortListing Model: A Streamlined SimplexDiffusion 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},
journal= {arXiv preprint arXiv:2508.17345},
year = {2025}
}