David Heurtel-Depeiges

Hi! I’m David Heurtel-Depeiges, a second year PhD Student at MILA - Québec AI Institute in Montreal, supervised by Sarath Chandar, Quentin Fournier, and a proud member of the FLAIR-bio lab

I am widely interested in Machine Learning but more specifically, my research interests are the following topics:

Deep Probabilistic Models with a focus on helping solve complex inference problems. Currently working on Discrete and Continuous Diffusion and Flows, Inverse Problems.
AI for Science: mainly in the context of Computational Biology (proteomics) and a side gig in Radio Astronomy.

Formerly, I was a Student Researcher at Google DeepMind, London, supervised by Anian Ruoss and Tim Genewein. Before that, I was also a Research Analyst at the Center for Computational Mathematics, Flatiron Institute, NY, where I was supervised by Bruno Regaldo-Saint Blancard and Ruben Ohana.

I graduated in 2024 from Ecole Polytechnique and the MVA program (Mathematics, Vision, Learning), which means that I belong to the X2020 class (yes, I know, it’s confusing, we number our classes from the first year of the program).

news

Aug 26, 2026	Started teaching INF8245AE — Machine Learning at Polytechnique Montréal as a lecturer!
Aug 26, 2024	Excited to start my PhD at MILA supervised by Sarath Chandar! Looking forward to working with the group and contributing to the community!
May 02, 2024	Our paper “Listening to the Noise: Blind Denoising with Gibbs Diffusion” has been accepted at ICML 2024. Will be going there in person!
Apr 19, 2024	Joined Google DeepMind as a Student Researcher for the next 4 months!

selected publications

bioRxiv

pLM representations unlock metagenomic space beyond homology

Lola Le Breton, David Heurtel-Depeiges, Douglas C. Millar, Lara E. Zetzsche, Robert M. Vernon, and 3 more authors

bioRxiv, 2026

DOI Bib PDF

@article{lebreton2026plm,
  title = {pLM representations unlock metagenomic space beyond homology},
  author = {Le Breton, Lola and Heurtel-Depeiges, David and Millar, Douglas C. and Zetzsche, Lara E. and Vernon, Robert M. and Langmead, Christopher James and Chandar, Sarath and Fournier, Quentin},
  year = {2026},
  journal = {bioRxiv},
  doi = {10.64898/2026.07.28.739874},
  url = {https://www.biorxiv.org/content/10.64898/2026.07.28.739874v1},
}

ICML

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data

David Heurtel-Depeiges^*, Anian Ruoss^*, Joel Veness, and Tim Genewein

Forty-second International Conference on Machine Learning. *Equal contribution , 2025

To appear in ICML 2025

PDF

ICML

Listening to the noise: Blind Denoising with Gibbs Diffusion

David Heurtel-Depeiges, Charles Margossian, Ruben Ohana, and Bruno Régaldo-Saint Blancard

In Forty-first International Conference on Machine Learning, 2024

Bib PDF Code Poster

@inproceedings{heurte2023listening,
  title = {Listening to the noise: Blind Denoising with Gibbs Diffusion},
  author = {Heurtel-Depeiges, David and Margossian, Charles and Ohana, Ruben and R{\'e}galdo-Saint Blancard, Bruno},
  booktitle = {Forty-first International Conference on Machine Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=rmEgJ7bhuZ},
}