paper-with-me

Papers

Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time

2023-12-14 · Zixiang Chen, Huizhuo Yuan, YongQian Li, Yiwen Kou, Junkai Zhang, Quanquan Gu

Discrete diffusion models have emerged as powerful tools for high-quality data generation. Despite their success in discrete spaces, such as text generation tasks, the acceleration of discrete diffusion models remains under-explored. In this paper, we propose discrete non-Markov diffusion models (DNDM), which naturally induce the predetermined transition time set. This enables a training-free sampling algorithm that significantly reduces the number of function evaluations (i.e., calls to the neural network), making the sampling process much faster. Furthermore, we study the transition from finite to infinite step sampling, offering new insights into bridging the gap between discrete and continuous-time processes for discrete diffusion models. Extensive experiments on natural language generation and machine translation tasks demonstrate the superior performance of our method in terms of both generation speed and sample quality compared to existing methods for discrete diffusion models.

📄 PDF Abstract BibTeX arXiv:2312.09193

Code (1)

uclaml/dndm 공식 구현 pytorch

Tasks

Image GenerationMachine TranslationText Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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

Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster

2026-05-18 · Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar, Javier Zazo arxiv

Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with f…

Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models

2026-02-23 · Luhan Tang, Longxuan Yu, Shaorong Zhang, Greg Ver Steeg arxiv

Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with parallel updates. However, their evaluation is challenging: existing metrics…

Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion

2025-06-10 · Alan N. Amin, Nate Gruver, Andrew Gordon Wilson

Discrete diffusion models, like continuous diffusion models, generate high-quality samples by gradually undoing noise applied to datapoints with a Markov process. Gradual generation in theory comes with many conceptual b…

Diffusion Models for Graphs Benefit From Discrete State Spaces

2022-10-04 · Kilian Konstantin Haefeli, Karolis Martinkus, Nathanaël Perraudin, Roger Wattenhofer

Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the generation of discrete graphs, they have, so f…

Denoising

Accelerated Diffusion Models via Speculative Sampling

2025-01-09 · Valentin De Bortoli, Alexandre Galashov, Arthur Gretton, Arnaud Doucet

Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribu…