ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation
Year: 2025
Type: preprint
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
Source: arXiv (Cornell University)
Authors: Song, Yuxuan, Zhang, Zhe, Pei, Yu, Gong, Jingjing, Yu, Qiying, Zhang, Zheng, Wang, Mingxuan, Zhou, Hao, Liu, Jingjing, Ma, Wei-Ying
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7077896157
Cites:
Cited by:
Related to: