Hadar Shavit

PhD candidate at the Chair of AI Methodology RWTH Aachen.

I am a PhD candidate at RWTH Aachen. My research focus is AutoAI methods, specifically algorithm configuration and selection with various applications. My specialisation is in empirical performance models, the machine learning models that predict the performance of algorithms without running them. These models play crucial roles in algorithm configuration and selection.

profile photo

News

  • Nov 2025: I got admitted to the AAAI Doctoral Consortium. If you are attending AAAI 26, please reach out!

Publications

The following is a list of my publications. For a complete list, please see my Google Scholar page.

GraphBench: Next-generation graph learning benchmarking


Timo Stoll, Chendi Qian, Ben Finkelshtein, Ali Parviz, Darius Weber, Fabrizio Frasca, Hadar Shavit, Antoine Siraudin, Arman Mielke, Marie Anastacio, Erik Müller, Maya Bechler-Speicher, Michael Bronstein, Mikhail Galkin, Holger Hoos, Mathias Niepert, Bryan Perozzi, Jan Tönshoff, Christopher Morris
ArXiv Preprint, 2025

Next Generation of Empirical Performance Prediction (AAAI Doctoral Consortium Thesis Summary)


Hadar Shavit
AAAI, 2024

ASF: Algorithm Selection Framework


Hadar Shavit, Holger H. Hoos
GitHub, 2024

A flexible python algorithm selection framework

Revisiting SATZilla Features in 2024


Hadar Shavit, Holger H. Hoos
SAT, 2024

A new version of the SATzilla feature extraction tool for SAT. Using our new version we achieved better performance for algorithm selection and empirical performance prediction.