发表机构
Brown University; University of Toronto; Sakana AI（布朗大学; 多伦多大学; Sakana AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出上下跳跃（JUD），首个面向离散有序数据的去噪器扩散模型家族，支持双向扰动，在不同数据模态上取得竞争性结果。
AI 中文摘要
扩散模型在连续空间中已高度发展，广泛应用于图像和视频领域。近期，针对类别数据的离散扩散模型取得了重大进展，尤其是在语言领域。相比之下，针对离散整数值数据的扩散模型发展较少，尽管这种模态普遍存在，涵盖从图像、音乐到基因计数等。我们提出了上下跳跃（JUD）——一种新的基于去噪器的离散有序数据扩散模型家族。这是首个以训练去噪器为中心的序数数据扩散模型家族，同时允许对数据进行双向（上下）扰动。训练目标的简洁性，结合双向扰动的灵活性，使我们在不同数据模态上获得了具有竞争力的结果。
英文摘要
Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion models for categorical data, specifically in the language domain. In contrast, diffusion models for discrete integer-valued data are less developed, despite the prevalence of this modality, ranging from images and music to gene counts. We introduce Jumping Up and Down (JUD)---a new family of denoiser-based diffusion models for discrete ordinal data. This is the first family of diffusion models for ordinal data which centers around training denoisers, which at the same time allows for bi-directional (up and down) perturbations of the data. The simplicity of the training objective, combined with the flexibility of bi-directional perturbations, leads us to obtain competitive results across different data modalities.
Comments39 pages, 3 figures
