Hugues Van Assel

Postdoctoral Fellow at Genentech · South San Francisco, CA

Portrait of Hugues Van Assel

I am a postdoctoral fellow at Genentech with Aviv Regev, working on machine learning for drug discovery. I develop methods in generative AI and self-supervised learning to make exploring complex biological design spaces more efficient.

Previously, I completed a PhD in mathematics at ENS Lyon, advised by Titouan Vayer and Aurélien Garivier, and visited the GalilAI group at Brown University. I studied at École Polytechnique and MVA.

Open Source

TorchDR Fast, state-of-the-art dimensionality reduction in PyTorch—from single-GPU to multi-GPU. stable-pretraining A PyTorch library for self-supervised pretraining with real-time monitoring.

Latest Posts

Nov 20, 2025 Joint-Embedding vs Reconstruction: When Should You Use Each?
Feb 25, 2024 Inverse optimal transport does not require unrolling

Selected Publications

For a complete publication list, see my Google Scholar profile.

  1. Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
    Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, and Aviv Regev
    arXiv preprint arXiv:2606.00514, 2026
    arXiv
  2. 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 HTML Blog Poster
  3. 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
  4. 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 HTML Poster