Email  /  Google Scholar  /  Github

Yue Song

I am a Computing & Mathematical Sciences postdoctoral research associate at Caltech, supervised by Yisong Yue, Pietro Perona, and Max Welling. I pursued doctoral studies under European Laboratory for Learning and Intelligent Systems (ELLIS), where I was 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.

I research Structured Representation Learning at the Science—AI Interface. Scientific data are inherently structured -- shaped by geometric, temporal, and topological regularities rooted in the laws of physics, biology, and chemistry. My research focuses on developing deep learning models that uncover and encode these structures, enabling more interpretable, generalizable, and data-efficient solutions across scientific domains.

Central to this agenda is a reciprocal philosophy: I leverage beneficial inductive biases from scientific disciplines -- such as differential geometries, dynamical systems, and computational neuroscience -- to inform the design of machine learning models (Science4AI), and in turn, use these structured models to deepen our understanding of complex scientific phenomena (AI4Science). My current research is not task-oriented; I do not focus on a particular ML task. Instead, I am interested in developing structured methods and finding appropriate applications in the broad scientific domain.

Prior to my Ph.D. studies, I received the B.Sc. cum laude from KU Leuven, Belgium and the joint M.Sc. summa cum laude from University of Trento, Italy and KTH Royal Institute of Technology, Sweden. Besides the technical master's degree, I received an Innovation & Entrepreneurship minor degree from European Institute of Innovation and Technology (EIT Digital).

• 2025/06: Our book Structured Representation Learning: From Homomorphisms and Disentanglement to Equivariance and Topography is now published with Springer Nature.
• 2025/04: Serve as Area Chair for NeurIPS 2025.
• 2024/02: Give CVPR and ECCV tutorials on disentangled&equivariant representation learning.

Web template © this.   All content © Yue Song
This page has been visited  times by  people.