paper-with-me

Papers

A Continuous Time Framework for Discrete Denoising Models

2022-05-30 · Andrew Campbell, Joe Benton, Valentin De Bortoli, Tom Rainforth, George Deligiannidis, Arnaud Doucet

We provide the first complete continuous time framework for denoising diffusion models of discrete data. This is achieved by formulating the forward noising process and corresponding reverse time generative process as Continuous Time Markov Chains (CTMCs). The model can be efficiently trained using a continuous time version of the ELBO. We simulate the high dimensional CTMC using techniques developed in chemical physics and exploit our continuous time framework to derive high performance samplers that we show can outperform discrete time methods for discrete data. The continuous time treatment also enables us to derive a novel theoretical result bounding the error between the generated sample distribution and the true data distribution.

📄 PDF Abstract BibTeX arXiv:2205.14987

Code (2)

andrew-cr/tauldr 공식 구현 pytorch
lingxiaoshawn/usd3 pytorch

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Unified Discrete Diffusion for Categorical Data

2024-02-06 · Lingxiao Zhao, Xueying Ding, Lijun Yu, Leman Akoglu

Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs. Although discrete-time discrete diffusion has been established for a while, only recently…

Denoising

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

2025-10-01 · Huangjie Zheng, Shansan Gong, Ruixiang Zhang, Tianrong Chen 외 arxiv

Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked …

Text Generation

Interleaved Gibbs Diffusion for Constrained Generation

2025-02-19 · Gautham Govind Anil, Sachin Yadav, Dheeraj Nagaraj, Karthikeyan Shanmugam 외

We introduce Interleaved Gibbs Diffusion (IGD), a novel generative modeling framework for mixed continuous-discrete data, focusing on constrained generation problems. Prior works on discrete and continuous-discrete diffu…

Denoising

In-Situ Tweedie Discrete Diffusion Models

2025-10-01 · Xiao Li, Jiaqi Zhang, Shuxiang Zhang, Tianshui Chen 외 arxiv

While diffusion models excel at generating continuous data such as images, adapting them to discrete tasks has relied on indirect approaches that either operate in continuous embedding spaces or use token masking mechani…

Image ClassificationText Generation

Discrete Stochastic Localization for Non-autoregressive Generation

2026-02-18 · Yunshu Wu, Jiayi Cheng, Longxuan Yu, Partha Thakuria 외 arxiv

Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not c…