paper-with-me

Papers

Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

2025-05-30 · Heli Ben-Hamu, Itai Gat, Daniel Severo, Niklas Nolte, Brian Karrer

Recent masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling. While most literature has focused on performance enhancing sampling procedures, efficient sampling from MDMs has been scarcely explored. We make the observation that often a given sequence of partially masked tokens determines the values of multiple unknown tokens deterministically, meaning that a single prediction of a masked model holds additional information unused by standard sampling procedures. Based on this observation, we introduce EB-Sampler, a simple drop-in replacement for existing samplers, utilizing an Entropy Bounded unmasking procedure that dynamically unmasks multiple tokens in one function evaluation with predefined approximate error tolerance. We formulate the EB-Sampler as part of a broad family of adaptive samplers for which we provide an error analysis that motivates our algorithmic choices. EB-Sampler accelerates sampling from current state of the art MDMs by roughly 2-3x on standard coding and math reasoning benchmarks without loss in performance. We also validate the same procedure works well on smaller reasoning tasks including maze navigation and Sudoku, tasks ARMs often struggle with.

📄 PDF Abstract BibTeX arXiv:2505.24857

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMath

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

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

2024-02-21 · Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff

Accelerated diffusion models hold the potential to significantly enhance the efficiency of standard diffusion processes. Theoretically, these models have been shown to achieve faster convergence rates than the standard $…

Denoising

Scaling Beyond Masked Diffusion Language Models

2026-02-16 · Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux 외 arxiv

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by st…

The Diffusion Duality, Chapter II: $Ψ$-Samplers

2026-02-24 · Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo arxiv

Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over autoregressive or Masked diffusion models in these settings. However, the…

Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximations

2025-10-29 · Hugo Lavenant, Giacomo Zanella arxiv

Recently proposed generative models for discrete data, such as Masked Diffusion Models (MDMs), exploit conditional independence approximations to reduce the computational cost of popular Auto-Regressive Models (ARMs), at…

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

2026-05-21 · Samson Gourevitch, Yazid Janati, Dario Shariatian, Umut Simsekli 외 arxiv

Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Models (MDM) these choices largely coincide,…