Hugues Van Assel

Postdoctoral Fellow at Genentech, South San Francisco CA

photo_profil.jpeg

I am a postdoc at Genentech with Aviv Regev.

I study the mathematical foundations of representation learning: how to extract compact, meaningful structure from high-dimensional data, using tools from probabilistic modeling and optimal transport.

Currently, I am interested in multi-modal and foundation models for high-throughput genomics data, and virtual screening and data selection for drug discovery.

Open-Source. I enjoy building and sharing open-source tools:

TorchDR
PyTorch toolbox for dimensionality reduction with state-of-the-art speed on single and multi-GPU.
PyTorch data-viz multi-GPU speed
stable-pretraining
PyTorch library for foundation model pretraining with real-time training monitoring.
PyTorch SSL Foundation Models

Background. I did my PhD in the math department of ENS Lyon on Optimal Transport and Probabilistic Modeling for Dimensionality Reduction. During my PhD, I visited the GalilAI group at Brown University to work on self-supervised learning. Prior to my PhD, I was a student at Ecole polytechnique and MVA.

We're hiring! Together with Edward De Brouwer, I am looking for a summer 2026 intern to work on Bayesian optimization with LLMs in the Regev Lab at Genentech, South San Francisco.

Apply here →  Feel free to reach out if you have questions. Come join us!


selected publications

  1. NeurIPS
    Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self-Supervised Learning
    Hugues Van Assel, Mark Ibrahim, Tommaso Biancalani, Aviv Regev, and Randall Balestriero
    Advances in Neural Information Processing Systems (Spotlight), 2025
    arXiv Blog Poster
  2. TMLR
    Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein
    Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty, Rémi Flamary, Pascal Frossard, and Titouan Vayer
    Transactions on Machine Learning Research, 2024
    arXiv
  3. NeurIPS
    SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
    Hugues Van Assel, Titouan Vayer, Rémi Flamary, and Nicolas Courty
    Advances in Neural Information Processing Systems, 2023
    arXiv Poster
  4. NeurIPS
    A Probabilistic Graph Coupling View of Dimension Reduction
    Hugues Van Assel, Thibault Espinasse, Julien Chiquet, and Franck Picard
    Advances in Neural Information Processing Systems, 2022
    arXiv Poster