Jacob Bamberger

DPhil in Computer Science at University of Oxford

prof_pic.jpg

Bonjour / Hej / Hi!

I am Jacob, a DPhil candidate at University of Oxford, supervised by Professor Michael Bronstein and Professor Xiaowen Dong. My research explores how tools from geometry, topology, and algebra – particularly differential geometry – can be used to tackle problems in modern deep learning, such as graph neural networks and generative models.

Before Oxford, I completed an MSc in Computer Science at EPFL. In a previous life, I was an aspiring mathematician: I earned a BSc and an MSc in Mathematics from McGill, where I focused on geometric group theory under the supervision of Professor Daniel Wise.

Along the way, I have also interned in various tech companies and startups, including Giotto.ai and Oracle Labs.

selected publications

  1. Preprint
    cdcfm_webpage.png
    Carré du champ flow matching: better quality-generalisation tradeoff in generative models
    Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, and Adam Gosztolai
    2025
    arXiv
  2. NeurIPS
    osq_stgnn.png
    Over-squashing in Spatiotemporal Graph Neural Networks
    Ivan Marisca, Jacob Bamberger, Cesare Alippi, and Michael M Bronstein
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
    arXiv
  3. ICML
    longrange.png
    On Measuring Long-Range Interactions in Graph Neural Networks
    Jacob Bamberger, Benjamin Gutteridge, Scott Roux, Michael M. Bronstein, and Xiaowen Dong
    In Forty-second International Conference on Machine Learning, 2025
    arXiv
  4. ICLR
    bunn.png
    Bundle Neural Network for message diffusion on graphs
    Jacob Bamberger, Federico Barbero, Xiaowen Dong, and Michael M. Bronstein
    In The Thirteenth International Conference on Learning Representations, 2025
    arXiv
  5. TAG in ML @ ICML
    universalcoverover.png
    A Topological Characterisation of Weisfeiler-Leman Equivalence Classes 
    Jacob Bamberger
    In Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, 2022
    arXiv