- 2025/06: Published book 'Structured Representation Learning: From Homomorphisms and Disentanglement to Equivariance and Topography' with Springer Nature.
- 2025/04: Served as Area Chair for NeurIPS 2025.
- 2024/02: Gave CVPR and ECCV tutorials on disentangled&equivariant representation learning.
- Multiple papers published in top conferences and journals such as NeurIPS, ICCV, CCN, ICLR, and T-PAMI.
Research Experience
- Postdoctoral Research Associate in Computing & Mathematical Sciences at California Institute of Technology (Caltech), supervised by Yisong Yue, Pietro Perona, and Max Welling.
- Will join the College of AI at Tsinghua University as a tenure-track Assistant Professor in Spring 2026, leading the Structured Representation Learning Lab (SRL Lab).
Education
- Ph.D.: European Laboratory for Learning and Intelligent Systems (ELLIS), affiliated with Multimedia and Human Understanding Group (MHUG) at University of Trento, Italy, and Amsterdam Machine Learning Lab (AMLab) at University of Amsterdam, the Netherlands, advised by Nicu Sebe and Max Welling.
- M.Sc.: Joint degree from University of Trento, Italy, and KTH Royal Institute of Technology, Sweden, summa cum laude.
- B.Sc.: KU Leuven, Belgium, cum laude. Also received a minor degree in Innovation & Entrepreneurship from European Institute of Innovation and Technology (EIT Digital).
Background
Research interests: Structured representation learning, particularly at the intersection of science and AI. Specializes in designing deep learning models that uncover and encode geometric, temporal, and topological regularities in scientific data, enhancing interpretability, generalizability, and data efficiency of solutions.