Alonso Urbano

My research interests include topics in Efficient Deep Learning and Geometric Deep Learning, with a focus on relaxations of equivariance, symmetry discovery, and learning inductive biases from data. My career goal is to build innovative learning algorithms that make a difference, pushing the boundaries of what is possible.

📬 Contact

office
Room 3024 at ZIB
e-mail
languages
Spanish and English

🎓 Curriculum vitae

since 2024
Researcher at ZIB

📝 Publications and preprints

Preprints

  1. Urbano, A., Romero, D. W., Zimmer, M., and Pokutta, S. (2025). RECON: Robust Symmetry Discovery Via Explicit Canonical Orientation Normalization. [arXiv]
    [BibTeX]
    @misc{2025_UrbanoWZimmerPokutta_Reconsymmetrydiscovery,
      archiveprefix = {arXiv},
      eprint = {2505.13289},
      primaryclass = {cs.LG},
      year = {2025},
      author = {Urbano, Alonso and Romero, David W. and Zimmer, Max and Pokutta, Sebastian},
      title = {RECON: Robust Symmetry Discovery Via Explicit Canonical Orientation Normalization},
      date = {2025-05-19}
    }

Conference proceedings

  1. Urbano, A., and Romero, D. W. (2024). Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries. Proceedings of the Geometry-Grounded Representation Learning and Generative Modeling Workshop (GRaM) at ICML 2024. [arXiv]
    [BibTeX]
    @inproceedings{2023_UrbanoRomero_Selfsupervisedsymmetries,
      year = {2024},
      booktitle = {Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) at ICML 2024},
      archiveprefix = {arXiv},
      eprint = {2312.12223},
      primaryclass = {cs.CV},
      author = {Urbano, Alonso and Romero, David W.},
      title = {Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries}
    }

💬 Talks and posters

Poster presentations

Jul 2024
Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries
Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) @ ICML 2024, Vienna