Dario Shariatian

PhD Student

INRIA Paris

Paris, France

I am a final-year PhD student at INRIA Paris (Sierra Project Team, led by Francis Bach). I work under the supervision of Umut Simsekli and Alain Durmus.

Before that, I obtained an MSc in Mathematics from the University of Oxford and a BSc/MSc from Ecole Polytechnique.

My work focuses broadly on methodology for generative models, especially continuous and discrete diffusion, with an interest in the interplay between probabilistic structure, empirical behavior, and scalable experimentation.

At the moment, I am especially interested in discrete diffusion models, as a compelling route toward faster generation, enabling multi-token generation per network call (see, e.g., Mercury). Yet, they admit important unresolved limitations, both algorithmic and structural, leaving substantial room for new ideas.

More details can be found in my CV.

selected publications

arXiv
Latent-Augmented Discrete Diffusion Models (LADD)

Dario Shariatian, Alain Durmus, and Stefano Peluchetti

arXiv preprint, Jan 2026

Abs Bib

We augment the masking process of diffusion language models with continuous latent embeddings, enabling cross-token modeling and improving few-step generation.
@article{shariatian2026ladd, title = {Latent-Augmented Discrete Diffusion Models (LADD)}, author = {Shariatian, Dario and Durmus, Alain and Peluchetti, Stefano}, journal = {arXiv preprint}, year = {2026}, month = jan }
NeurIPS
Algorithm and Data Dependent Generalization Bounds for Score-Based Generative Models

Dario Shariatian, Benjamin Dupuis, Maxime Haddouche, and 2 more authors

In Advances in Neural Information Processing Systems, Sep 2025

Abs arXiv Bib Code

We establish generalization bounds for diffusion models that account jointly for optimization dynamics and data distribution, together with supporting empirical results.
@inproceedings{shariatian2025generalization, title = {Algorithm and Data Dependent Generalization Bounds for Score-Based Generative Models}, author = {Shariatian, Dario and Dupuis, Benjamin and Haddouche, Maxime and Durmus, Alain and Simsekli, Umut}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, month = sep, }
ICML
Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions

Dario Shariatian, Le-Tuyet-Nhi Pham, Antonio Ocello, and 2 more authors

In International Conference on Machine Learning, Feb 2025

Abs arXiv Bib Code

We develop a discrete diffusion method for bit data that outperforms MD4 and Discrete Flow Matching on binarized MNIST while using about 2.5x fewer network evaluations, with supporting theoretical analysis.
@inproceedings{shariatian2025dmpm, title = {Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions}, author = {Shariatian, Dario and Pham, Le-Tuyet-Nhi and Ocello, Antonio and Conforti, Giovanni and Durmus, Alain}, booktitle = {International Conference on Machine Learning}, year = {2025}, month = feb, }

ICLR

Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models

Dario Shariatian, Umut Simsekli, and Alain Durmus

In International Conference on Learning Representations, Jan 2025

Abs arXiv Bib Code Slides

@inproceedings{shariatian2025dlpm,
  title = {Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models},
  author = {Shariatian, Dario and Simsekli, Umut and Durmus, Alain},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  month = jan,
}

NeurIPS
Piecewise Deterministic Generative Models

Andrea Bertazzi, Dario Shariatian, Umut Simsekli, and 2 more authors

In Advances in Neural Information Processing Systems, Jul 2024

Abs arXiv Bib Code

We introduce a class of generative models based on piecewise-deterministic Markov processes, combining deterministic motion with random jumps, and report promising empirical results.
@inproceedings{bertazzi2024pdmp, title = {Piecewise Deterministic Generative Models}, author = {Bertazzi, Andrea and Shariatian, Dario and Simsekli, Umut and Moulines, {\'E}ric and Durmus, Alain}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, month = jul, }