arXiv：cs.LG· Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti·· 3 小时前AI 评分31
JUD：面向离散有序数据的去噪器扩散模型
Jumping up and down: Denoiser diffusion models for discrete ordinal data
AI 导读
研究者提出 Jumping Up and Down（JUD），首个以训练去噪器为核心的离散有序数据扩散模型家族，支持数据双向（上、下）扰动。其训练目标简单，在图像、音乐、基因计数等多种数据模态上取得有竞争力的结果。
正文
Abstract: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.
| Comments: | 39 pages, 3 figures |
| Subjects: | Machine Learning (cs.LG); Methodology (stat.ME) |
| Cite as: | arXiv:2610.02754 [cs.LG] |
| (or arXiv:2610.02754v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02754 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ricardo Baptista [view email]
[v1]
Fri, 2 Oct 2026 03:31:07 UTC (3,598 KB)
来源：arXiv：cs.LG · arxiv.org