Giulio Viganò

PhD @ University of Milano-Bicocca.

I am a PhD researcher in Computer Science at the University of Milano-Bicocca, working at the intersection of machine learning and geometry.

My research focuses on developing neural architectures to understand and model correspondences between 3D shapes, and to use geometry as a lens to undestrand pretrained models. I am passionate about finding realtions between apparently differently concepts, like in different areas of math and between math and applied subjects. During my Phd, I spent aperiod viting LiX at École Polytechnique near Paris, where I explored how geometric reasoning can advance our understanding of Large Languange Models.

Previously, I earned a Master’s degree in Applied Mathematics from the University of Milan.

When I’m not working, you’ll find me at the bar discussing politics but also enjoying the essentials of Italian life: food and footbal.

Research Interests

  • Geometric Deep Learning
  • Spectral Geometry
  • Machine Learning

news

Jun 18, 2026 🎉 Our paper FUSE: A Flow-based Mapping Between Shapes (with L. Olearo, F. Maggioli, D. Baieri and S. Melzi) has been accepted at ECCV2026.
Nov 01, 2025 🇫🇷 I joined École Polytechnique as a Visiting PhD Student, working with Maks Ovsjanikov.
Sep 30, 2025 📚 We have released GeomFum, a new library for machine learning with Functional Maps! Check it out on https://github.com/3diglab/geomfum.
Aug 10, 2025 🎉 Our paper NAM: Neural Adjoint Maps for refining shape correspondences (with Maks Ovsjanikov and Simone Melzi) has been published in ACM Transactions on Graphics! Currently in Vancouver at SIGGRAPH 2025 presenting our work.

latest posts

selected publications

  1. fuse.png
    FUSE: A Flow-based Mapping Between Shapes
    Lorenzo Olearo, Giulio Viganò, Daniele Baieri, and 2 more authors
    European Conference on Computer Vision (ECCV 2026), 2026
  2. nam.png
    NAM: Neural Adjoint Maps for Refining Shape Correspondences
    Giulio Viganò, Maks Ovsjanikov, and Simone Melzi
    ACM Transactions on Graphics (TOG), 2025