Teodora Reu

DPhil in Computer Science at University of Oxford

prof_pic.jpeg

Hey! I’m Teo, a DPhil student at Oxford working with Professor Michael Bronstein on generative models (diffusion, flow matching, optimal transport) and geometric deep learning. I’ve published at NeurIPS 2024/2025 (Spotlight!) and UAI 2024, and recently interned at Wayve training large-scale video autoencoders for autonomous driving.

But my true passion? Pure math! I was a counsellor at PROMYS teaching Number Theory and Group Theory to IMO-level students, basically living my best life!

Oh, and when I’m not doing math or ML, I paint! Check out my art portfolio for oils and watercolors.

selected publications

  1. failure_flow.png
    Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
    Teodora Reu, Sixtine Dromigny, Michael Bronstein, and Francisco Vargas
    Advances in Neural Information Processing Systems (NeurIPS 2025, Spotlight), 2025
    arXiv HTML
  2. metric_flow.png
    Metric flow matching for smooth interpolations on the data manifold
    Kacper Kapuśniak, Peter Potaptchik, Teodora Reu, Leo Zhang, and 4 more authors
    Advances in Neural Information Processing Systems, 2024
    HTML
  3. diff.png
    Expressiveness Remarks for Denoising Diffusion Based Sampling
    Francisco Vargas, Teodora Reu, and Anna Kerekes
    In Fifth Symposium on Advances in Approximate Bayesian Inference, 2023
    HTML
  4. cin.png
    Topological message passing for higher-order and long-range interactions
    Lorenzo Giusti, Teodora Reu, Francesco Ceccarelli, Cristian Bodnar, and 1 more author
    In 2024 International Joint Conference on Neural Networks (IJCNN), 2024
    HTML