paper-with-me

Papers

A Reparameterized Discrete Diffusion Model for Text Generation

2023-02-11 · Lin Zheng, Jianbo Yuan, Lei Yu, Lingpeng Kong

This work studies discrete diffusion probabilistic models with applications to natural language generation. We derive an alternative yet equivalent formulation of the sampling from discrete diffusion processes and leverage this insight to develop a family of reparameterized discrete diffusion models. The derived generic framework is highly flexible, offers a fresh perspective of the generation process in discrete diffusion models, and features more effective training and decoding techniques. We conduct extensive experiments to evaluate the text generation capability of our model, demonstrating significant improvements over existing diffusion models.

📄 PDF Abstract BibTeX arXiv:2302.05737

Code (1)

hkunlp/reparam-discrete-diffusion 공식 구현 pytorch

Tasks

modelText Generation

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

Categorical Reparameterization with Denoising Diffusion models

2026-01-02 · Samson Gourevitch, Alain Durmus, Eric Moulines, Jimmy Olsson 외 arxiv

Learning models with categorical variables requires optimizing expectations over discrete distributions, a setting in which stochastic gradient-based optimization is challenging due to the non-differentiability of catego…

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

2024-06-06 · Jingyang Ou, Shen Nie, Kaiwen Xue, Fengqi Zhu 외

Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, …

DenoisingLanguage ModelingLanguage Modelling

A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching

2026-06-23 · Feiyang Fu, Hehe Fan arxiv

Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics. In practice, sampling for DFM commonly employs discretizations such…

Text Generation

Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function

2025-12-04 · Hyeongyu Kang, Jaewoo Lee, Woocheol Shin, Kiyoung Om 외 arxiv

Diffusion models excel at generating high-likelihood samples but often require alignment with downstream objectives. Existing fine-tuning methods for diffusion models significantly suffer from reward over-optimization, r…

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

2023-12-14 · Zixiang Chen, Huizhuo Yuan, YongQian Li, Yiwen Kou 외

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 un…

Image GenerationMachine TranslationText Generation