Doctoral Student
Email: [email protected]
Ivo Petrov
About me:
I am Ivo Petrov, second-year PhD student at the Institute for Computer Science, Artificial Intelligence and Technology, Sofia University, starting September 2024, working on creating secure, safe, and trustworthy AI in Prof. Martin Vechev’s group.
My interests lie in the fields of applicable AI, computer vision, mathematical modelling and reliable ML systems.
Education
– University of Cambridge, United Kingdom, September 2023 – July 2024
MPhil in Data-Intensive Science
– University of Cambridge, United Kingdom October 2020 – June 2023
B.A. Hons in Computer Science (First Class)
Awards
International Mathematics Olympiad 2019 – Silver Medal
International Physics Olympiad 2019 – Silver Medal
International Physics Olympiad 2018 – Silver Medal
All-Russian Mathematics Olympiad 2018 – Gold Medal
European Science Olympiad 2018 – Silver Medal
Junior Balkan Mathematics Olympiad 2016 – Silver Medal
Relevant Experience
Jump Trading, London, UK, 06/23 – 09/23
Quantitative ResearchIntern
Optiver, Amsterdam, Netherlands, 06/22 – 08/22
Quantitative ResearchIntern
2025
Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar I. Dimitrov, Martin Vechev
GRAIN: Exact Graph Reconstruction from Gradients
In: International Conference on Learning Representations (ICLR 2025)
Mislav Balunović, Jasper Dekoninck, Nikola Jovanović, Ivo Petrov, Martin Vechev
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
In: International Conference on Machine Learning (ICML 2025); ICLR 2025 (Workshop)
Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev, Maria Drencheva, Kristian Minchev, Mislav Balunović, Nikola Jovanović, Martin Vechev
Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
In: International Conference on Machine Learning (ICML 2025) (Workshop)
Jasper Dekoninck, Ivo Petrov, Kristian Minchev, Mislav Balunovic, Martin Vechev, Miroslav Marinov, Maria Drencheva, Lyuba Konova, Milen Shumanov, Kaloyan Tsvetkov, Nikolay Drenchev, Lazar Todorov, Kalina Nikolova, Nikolay Georgiev, Vanesa Kalinkova, Margulan Ismoldayev
The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs
In: International Conference on Machine Learning (ICML 2025) (Workshop)
Ivo Petrov, Jasper Dekoninck, Martin Vechev
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
In: ACM OOPSLA 2025
2024
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
DAGER: Exact Gradient Inversion for Large Language Models
In: Conference on Neural Information Processing Systems (NeurIPS 2024)
