About me

I am a PhD candidate at CISPA Helmholtz Center for Information Security in Saarland, Germany, supervised by Dr. Rebekka Burkholz at the Relational ML Lab.

I study ways to improve the generalization of graph neural networks (GNNs), with a focus on how graph structure and depth affect their behavior in theory and practice. I have worked on directions such as rewiring, tabularization, regularization, and knowledge distillation, with an emphasis on empirical evaluation and testing the limits of common assumptions. More broadly, I am interested in developing architectures that balance the trade-offs between expressiveness, efficiency, and generalization; in this regard, I have collaborated on broader topics such as tabular model robustness and optimization. My work has been published at NeurIPS, ICLR, and ICML [1, 2, 3] and presented in several talks and workshops.

My CV is available here.

Background

I obtained two undergraduate degrees in Mathematics and Computer Science from Universidad Complutense de Madrid. Then I was awarded the prestigious postgraduate fellowship from la Caixa Foundation, which fully supported my master’s studies in Advanced Computer Science with Artificial Intelligence at the University of Strathclyde in the UK. I was awarded the Departmental Best Overall Performance Prize.

Since 2023, I annually attend the European Girls’ Mathematical Olympiad (EGMO) as IT support; I was a contestant in 2017. I have been selected twice for the Heidelberg Laureate Forum (HLF), in 2022 and 2026. I have also developed two music notation packages for LaTeX: mousik (2026) and ddphonism (2019).

Upcoming

• December 2026｜One co-authored paper on memorization at NeurIPS’26, and one first-author paper on regularization at the UniReps workshop.

• September 2026｜I have been selected to attend the 13th Heidelberg Laureate Forum (HLF) as a young researcher for a second time. I also participated in their science-art exhibition ISAP.

Recent

• July 2026｜First-author paper at ICML’26: Fixed aggregation features can rival GNNs, and two workshop posters at GFM and MemFM. I was also selected as a Gold Reviewer (25%).

• June 2026｜Invited talk at the AI Security Afternoon at Universität des Saarlandes.

• June 2026｜An oral and a poster at the Graph Signal Processing Workshop (GSP).

• April 2026｜Three co-authored papers on confounding and optimization at ICLR’26 [a b c]. I was also selected among the Top 200 Reviewers (1%).

• March 2026｜Three Recent Spotlight posters at the Conference on Parsimony and Learning (CPAL).

• March 2026｜Math Olympiad trainer at the International EGMO Preparatory Seminar in Bonn.

Older events are shown in the timeline.