Stefan Balauca

Doctoral Student

Email: [email protected]

About me

I am Stefan Balauca, a first year doctoral student at the Institute for Computer Science, Artificial Intelligence and Technology, Sofia University from October 2023, working in the field of machine learning. I am supervised by Prof. Martin Vechev.

My interests include Deep Learning, robust and reliable ML systems, adversarial learning, bioinformatics, and Quantum Computing.

Education

  • Al. I. Cuza University of Iași, Romania, October 2021 – July 2023
    Research M.Sc. – Artificial Intelligence and Quantum Computing
  • Al. I. Cuza University of Iași, Romania, October 2018 – July 2021
    B.Sc. in Computer Science
  • Al. I. Cuza University of Iași, Romania, October 2018 – July 2022
    B.Sc. in Technological Physics

Awards

  • International Mathematics Competition for University Students, 2021 – Silver Medal
  • South-Eastern Europe Mathematical Olympiad for University Students, 2020 – Gold Medal
  • South Eastern Europe Mathematical Olympiad for University Students 2019 – Silver Medal
  • International Ariel Mathematical Olympiad, 2019, 2020 – Gold Medals
  • Asiatic Physics Olympiad, 2018 – Gold Medal
  • International Earth Sciences Olympiad, 2017 – Gold Medal
  • International Linguistics Olympiad, 2017 – Bronze Medal
  • Junior Balkan Mathematical Olympiad, 2015 – Silver Medal
  • International Junior Sciences Olympiad, 2014, 2015 – Silver Medals

Publications

Efficient Constructions for Simulating Multi Controlled Quantum Gates 
Stefan Balauca, Andreea Arusoaie
International Conference on Computational Science 2022, London, UK

Relevant Experience

  • Stem Cell Institute, University of Cambridge, UK 05/2023 – 09/2023
    Research Intern – Machine Learning in Bioinformatics
  • Al. I. Cuza University of Iași, Romania, 10/2021 – 07/2023
    Teaching Assistant, Machine Learning, Numerical Methods and Quantum Computing
  • University of Maryland, College Park, MD, US, 07/2021 – 10/2021
    Research Intern – Machine Learning in Malware Detection

2025

Ada-Astrid Balauca, Sanjana Garai, Stefan Balauca, Rasesh Udayakumar Shetty, Naitik Agrawal, Dhwanil Subhashbhai Shah, Yuqian Fu, Xi Wang, Kristina Toutanova, Danda Pani Paudel, Luc Van Gool
Understanding Museum Exhibits using Vision-Language Reasoning
In: International Conference on Computer Vision (ICCV 2025)

Paper

Csaba Dékány, Stefan Balauca, Robin Staab, Dimitar I. Dimitrov, Martin Vechev
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

Paper

Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations
In: Transactions on Machine Learning Research (TMLR 2025)

Paper

Yuhao Mao, Stefan Balauca, Martin Vechev
CTBENCH: A Library and Benchmark for Certified Training
In: 2025 Forty-Second International Conference on Machine Learning (ICML 2025)

Paper