PhD Position F/M Theory for Discrete Diffusion Models

1000scholars; Paris; Hybrid; EUR 20,000 - 27,000; Full time

Job summary

Inria Paris is offering a PhD position in Theory for Discrete Diffusion Models within the DYNASTY ERC Starting Grant. The role focuses on theoretical foundations and empirical validation, with possible conference travel and paper presentations.

The candidate will work on generalization, statistical analyses and experiments to validate theory. The successful applicant will contribute to multiple high-impact publications and collaboration across the project, with a start date of Jan 2027 and a

Qualifications

• High level of professional/academic English.
• Proficient coding in Python with DL libraries.

Responsibilities

• Conduct theoretical research.
• Conduct experiments for empirical verification.
• Write scientific articles.
• Disseminate the scientific work in appropriate venues.

Skills

English language

Python

Tools

PyTorch

NumPy

Job description

# PhD Position F/M Theory for Discrete Diffusion ModelsInria ParisParis, FrancePhD / DoctoralDeep Learning29 days left## About the position**Context**The PhD position will be in the framework of the ERC Starting Grant DYNASTY (Dynamics-Aware Theory of Deep Learning). The position might include traveling to conferences for paper presentation. Travel expenses will be covered within the limits of the scale in force.**Assignment**Discrete diffusion models have become a leading alternative to autoregressive models for generating text and other categorical data [1, 2]. They generate samples by reversing a Markov chain that progressively corrupts the data, using a score function learned by a neural network [1]. Despite their empirical success, their theoretical understanding remains far less developed than that of their continuous counterparts. The objective of this PhD is to study the theoretical foundations of discrete diffusion models, and in particular how well they learn and generalize when the score is estimated by a neural network. Building on recent statistical analyses [3, 4] and on generalization bounds for diffusion models [5], the project will investigate how statistical, approximation and optimization errors affect the quality of the generated samples, and will validate the theory through numerical experiments. References [1] A. Lou, C. Meng, S. Ermon. Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution. ICML, 2024. [2] S. S. Sahoo, M. Arriola, Y. Schiff, A. Gokaslan, E. Marroquin, J. T. Chiu, A. Rush, V. Kuleshov. Simple and Effective Masked Diffusion Language Models. NeurIPS, 2024. [3] Z. Zhang, H. Fu, Z. Yang, M. Wang, T. Zhao, M. Chen. Generalization Bounds for Discrete Diffusion: Statistical Advantage of Masking. ICML, 2026. [4] L. Blunda, T. Farghly, U. Şimşekli, A. Durmus. Discrete Diffusion Models are Minimax Optimal Under Sparsity. arXiv:2610.19020, 2026. [5] B. Dupuis, D. Shariatian, M. Haddouche, A. Durmus, U. Şimşekli. Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models. arXiv:2506.03849, 2026.**Main activities**Conduct theoretical research Conduct experiments for empirical verification Write scientific articlesDisseminate the scientific work in appropriate venues.**Skills**Technical skills and level required : Languages : High-level of professional/academic English Coding skills : Good level of coding in Python and related deep learning librariesThis listing was collected from a public source and is reproduced here forinformation only. Always confirm the details on the original posting before applying. View the original postingApply on the source siteTakes you to Inria Paris.Deadline: 03 Dec 2026Starts: 01 Jan 2027Duration: 3 yearsPosted: 04 Nov 2026Institution: Inria ParisLocation: Paris, France