About me
I am a second-year PhD candidate at the Relational ML Lab, supervised by Dr. Rebekka Burkholz, at the CISPA Helmholtz Center for Information Security in Saarland, Germany. My research addresses generalization challenges in graph learning, particularly by studying the dual role of input graphs as both data and computation structures, and the effects of modifying them under different criteria. The work has been published at NeurIPS and ICLR, and presented at multiple talks: HAICON, Cohere4AI, NetSci.
I hold two degrees in Mathematics and Computer Science from Universidad Complutense de Madrid, and I received the prestigious postgraduate fellowship from la Caixa Foundation in 2022. It allowed me to study a master’s at Strathclyde in Glasgow, UK, where I was awarded the Best Overall Performance Prize. I annually participate in organizing the European Girls’ Mathematical Olympiad (EGMO) as part of the IT team. I was featured in the Nova 111 Student List 2023 as one of the top 10 under 25 in Computer Science in Spain, and was selected for the 9th Heidelberg Laureate Forum in 2022. My passion for music and LaTeX inspired me in 2019 to publish a package, ddphonism, now included in MikTeX and the TeXLive Music bundle.
You can read my full CV here or view a timeline of all my past activities.
News
-
April 2025|First-author paper at ICLR’25: GNNs getting ComFy: Community and feature similarity guided rewiring. Featured in the TLDR AI newsletter. Also presented at the WiML workshop NeurIPS’24.
-
February 2025|Talk for Cohere4AI: Rewiring Graph Neural Networks: When less is more and structure matters.
-
December 2024|First-author paper at NeurIPS’24: Spectral graph pruning against over-squashing and over-smoothing.
-
June 2024|Talk at Helmholtz AI Conference 2024: AI for Science (HAICON).