Variational Masked Diffusion Models

• URL: http://arxiv.org/abs/2510.23606v1
• Date: Mon, 27 Oct 2025 17:59:57 GMT
• Title: Variational Masked Diffusion Models
• Authors: Yichi Zhang, Alex Schwing, Zhizhen Zhao,
• Abstract summary: Variational Masked Diffusion (VMD) is a framework that introduces latent variables into the masked diffusion process.<n>We demonstrate that VMD successfully learns dependencies that conventional masked diffusion fails to capture.
• Score: 8.801239075625151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked diffusion models have recently emerged as a flexible framework for discrete generative modeling. However, a key limitation of standard masked diffusion is its inability to effectively capture dependencies among tokens that are predicted concurrently, leading to degraded generation quality when dependencies among tokens are important. To explicitly model dependencies among tokens, we propose Variational Masked Diffusion (VMD), a framework that introduces latent variables into the masked diffusion process. Through controlled experiments on synthetic datasets, we demonstrate that VMD successfully learns dependencies that conventional masked diffusion fails to capture. We further validate the effectiveness of our approach on Sudoku puzzles and text datasets, where learning of dependencies among tokens improves global consistency. Across these domains, VMD enhances both generation quality and dependency awareness, highlighting the value of integrating variational inference into masked diffusion. Our code is available at: https://riccizz.github.io/VMD.

Related papers

• Training-Free Self-Correction for Multimodal Masked Diffusion Models [61.84305395626145]
  We propose a training-free self-correction framework that exploits the inductive biases of pre-trained masked diffusion models.<n>Our method significantly improves generation quality on text-to-image generation and multimodal understanding tasks with reduced sampling steps.
  arXiv  Detail & Related papers  (2026-02-02T23:58:15Z)
• Learning Unmasking Policies for Diffusion Language Models [33.44995119635116]
  Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks.<n>One particularly successful variant is masked discrete diffusion, in which a buffer filled with special mask tokens is progressively replaced with tokens sampled from the model's vocabulary.<n>In this work, we propose to train sampling procedures using reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-09T20:44:33Z)
• Latent Discrete Diffusion Models [18.979326092796896]
  We study discrete diffusion for language and other categorical data.<n>We propose emphLatent Discrete Diffusion Models (LDDM)<n>We present two instantiations: (i) FUJI-LDDMs, which perform fully joint denoising of tokens and latents, and (ii) SEQ-LDDMs, which sequentially resolve the latent and then the discrete chain conditionally on it.<n>For both variants we derive ELBO-style objectives and discuss design choices to learn informative latents yet amenable to diffusoin modeling.
  arXiv  Detail & Related papers  (2025-10-20T21:26:52Z)
• On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning [14.707830064594056]
  Diffusion autoencoders (DAs) use an input-dependent latent variable to capture representations alongside the diffusion process.<n>Better generative modelling is the primary goal of another class of diffusion models -- those that learn their forward (noising) process.
  arXiv  Detail & Related papers  (2025-05-30T18:14:09Z)
• Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling [48.96034602889216]
  Variencoding Discrete Diffusion (VADD) is a novel framework that enhances discrete diffusion with latent variable modeling.<n>By introducing an auxiliary recognition model, VADD enables stable training via variational lower bounds and amortized inference over the training set.<n> Empirical results on 2D toy data, pixel-level image generation, and text generation demonstrate that VADD consistently outperforms MDM baselines.
  arXiv  Detail & Related papers  (2025-05-23T01:45:47Z)
• DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers [86.5541501589166]
  DiffMoE is a batch-level global token pool that enables experts to access global token distributions during training.<n>It achieves state-of-the-art performance among diffusion models on ImageNet benchmark.<n>The effectiveness of our approach extends beyond class-conditional generation to more challenging tasks such as text-to-image generation.
  arXiv  Detail & Related papers  (2025-03-18T17:57:07Z)
• Generalized Interpolating Discrete Diffusion [65.74168524007484]
  Masked diffusion is a popular choice due to its simplicity and effectiveness.<n>We generalize a new family of general interpolating discrete diffusion (GIDD) which offers greater flexibility in the design of the noising processes.<n>Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality.
  arXiv  Detail & Related papers  (2025-03-06T14:30:55Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• A Cheaper and Better Diffusion Language Model with Soft-Masked Noise [62.719656543880596]
  Masked-Diffuse LM is a novel diffusion model for language modeling, inspired by linguistic features in languages. Specifically, we design a linguistic-informed forward process which adds corruptions to the text through strategically soft-masking to better noise the textual data. We demonstrate that our Masked-Diffuse LM can achieve better generation quality than the state-of-the-art diffusion models with better efficiency.
  arXiv  Detail & Related papers  (2023-04-10T17:58:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.