提出一种基于单纯形的简化扩散模型，用于高效生成离散序列。
ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation
- 通过单纯形中心点建模，减少生成复杂度
- 在DNA和蛋白质设计任务中达到领先性能
- 适合需要高质量离散序列生成的研究者
离散变量生成在自然语言处理和生物序列设计中至关重要但极具挑战。我们提出短列表模型（Shortlisting Model, SLM），一种受渐进候选筛选启发的新型基于单纯形的扩散模型。SLM 在单纯形中心点上操作，显著降低生成复杂度并提升可扩展性。此外，其灵活实现的无分类器引导机制有效提升了无条件生成性能。在DNA启动子与增强子设计、蛋白质设计、字符级及大词汇量语言建模任务上的大量实验表明，SLM 具有竞争力的性能和强大潜力。代码已开源：https://github.com/GenSI-THUAIR/SLM。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。