Eduardo Santos-Escriche

ELLIS PhD Student · Technical University of Munich

I am an ELLIS PhD student in the Department of Computer Science at the Technical University of Munich. I work in the Foundations of Deep Neural Networks group, led by Prof. Stefanie Jegelka, and I am co-supervised by Prof. Pietro Liò at the Department of Computer Science and Technology of the University of Cambridge.

Research Interests:

Geometric Deep Learning
AI4Science
Graph Neural Networks

I am always open to new collaborations and happy to supervise motivated students for theses or projects in CS. Feel free to reach out!

Publications

LieAugmenter: Equivariant Learning by Discovering Symmetries with Learnable Augmentations

Eduardo Santos-Escriche , Ya-Wei Eileen Lin , Stefanie Jegelka

arXiv, 2025

Data augmentation for geometric domains typically requires underlying symmetries to be specified a priori, which can limit generalization in cases where the symmetries are unknown or approximate. To address this, we introduce LieAugmenter, an end-to-end framework that discovers task-relevant continuous symmetries through learnable augmentations parameterized by Lie groups.

Paper