paper-with-me

Papers

Continuous diffusion for categorical data

2022-11-28 · Sander Dieleman, Laurent Sartran, Arman Roshannai, Nikolay Savinov, Yaroslav Ganin, Pierre H. Richemond, Arnaud Doucet, Robin Strudel, Chris Dyer, Conor Durkan, Curtis Hawthorne, Rémi Leblond, Will Grathwohl, Jonas Adler

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

📄 PDF Abstract BibTeX arXiv:2211.15089

Code (0)

등록된 구현이 없습니다.

Tasks

Language Modelling

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

Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions

2021-02-10 · NeurIPS 2021 12 · Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré 외

Generative flows and diffusion models have been predominantly trained on ordinal data, for example natural images. This paper introduces two extensions of flows and diffusion for categorical data such as language or imag…

DenoisingImage SegmentationLanguage ModellingSegmentation+1

Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data

2026-07-25 · Yuefei Shen, Xiaotong Shen arxiv

Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euclidean spaces, whereas categorical laws lie on probability simplices a…

Diffusing Gaussian Mixtures for Generating Categorical Data

2023-03-08 · Florence Regol, Mark Coates

Learning a categorical distribution comes with its own set of challenges. A successful approach taken by state-of-the-art works is to cast the problem in a continuous domain to take advantage of the impressive performanc…

Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech

2026-06-08 · Vadim Popov, Wenju Gu, Tasnima Sadekova, Georgii Aparin 외 arxiv

Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data. The scientific interest to such models has been constantly increasing these days because …

Continuous Diffusion Model for Language Modeling

2025-02-17 · Jaehyeong Jo, Sung Ju Hwang

Diffusion models have emerged as a promising alternative to autoregressive models in modeling discrete categorical data. Yet diffusion models that directly work on discrete data space do not fully exploit the power of it…

Language ModelingLanguage Modellingmodel