Infinite Mask Diffusion Models use stochastic infinite-state masks to overcome the factorization error lower bound in standard masked diffusion, achieving superior few-step performance on language tasks via distillation.
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively unmasking multiple dimensions from an all-masked input, but their performance can degrade when using few denoising steps due to limited modeling of inter-dimensional dependencies. In this paper, we propose Variational Autoencoding Discrete Diffusion (VADD), a novel framework that enhances discrete diffusion with latent variable modeling to implicitly capture correlations among dimensions. By introducing an auxiliary recognition model, VADD enables stable training via variational lower bounds maximization and amortized inference over the training set. Our approach retains the efficiency of traditional MDMs while significantly improving sample quality, especially when the number of denoising steps is small. Empirical results on 2D toy data, pixel-level image generation, and text generation demonstrate that VADD consistently outperforms MDM baselines in sample quality with few denoising steps.
years
2026 3representative citing papers
OeMDM unifies masked diffusion, autoregressive, and block diffusion models under various generation orders; LoMDM jointly optimizes ordering and diffusion backbone from scratch and outperforms prior discrete diffusion models on language benchmarks.
citing papers explorer
-
Infinite Mask Diffusion for Few-Step Distillation
Infinite Mask Diffusion Models use stochastic infinite-state masks to overcome the factorization error lower bound in standard masked diffusion, achieving superior few-step performance on language tasks via distillation.
-
Unifying Masked Diffusion Models with Various Generation Orders and Beyond
OeMDM unifies masked diffusion, autoregressive, and block diffusion models under various generation orders; LoMDM jointly optimizes ordering and diffusion backbone from scratch and outperforms prior discrete diffusion models on language benchmarks.
- Learned Relay Representations for Forward-Thinking Discrete Diffusion Models