activity
20242026
collaborators

6 papers

cs.LG2026

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

Samson Gourevitch, Yazid Janati, Dario Shariatian +4

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 Mode…

cs.LG2026

Latent-Augmented Discrete Diffusion Models

Dario Shariatian, Alain Durmus, Umut Simsekli +1

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored rev…

stat.ML2026

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models

Benjamin Dupuis, Dario Shariatian, Maxime Haddouche +2

Score-based generative models (SGMs) have emerged as one of the most popular classes of generative models. A substantial body of work now exists on the analysis of SGMs, focusing e…

stat.ML2025

Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions

Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello +2

This paper introduces Discrete Markov Probabilistic Models (DMPMs), a novel discrete diffusion algorithm for discrete data generation. The algorithm operates in discrete bit space,…

cs.LG2025

Heavy-Tailed Diffusion with Denoising Lévy Probabilistic Models

Dario Shariatian, Umut Simsekli, Alain Durmus

Exploring noise distributions beyond Gaussian in diffusion models remains an open challenge. While Gaussian-based models succeed within a unified SDE framework, recent studies sugg…

stat.ML2024

Piecewise deterministic generative models

Andrea Bertazzi, Dario Shariatian, Umut Simsekli +2

We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), a family of non-diffusive stochastic processes consisting of deterministi…