Summer Undergraduate Research Fellow
Email: [email protected]
Margulan Ismoldayev
About:
I am Margulan Ismoldayev, a research intern at INSAIT in the summer of 2025, working with Dr. Dimitar Dimitrov, Prof. Martin Vechev and Ivo Petrov. I am an undergraduate student in Computer Science and Physics at MIT. My project focuses on the security of Federated Learning, specifically studying ‘gradient leakage’ attacks that can reconstruct private images from model updates. I am particularly investigating the privacy vulnerabilities of modern Vision Transformers (ViTs) and Vision-Language Models (VLMs).
Education:
Massachusetts Institute of Technology (MIT), Cambridge, MA September 2023 – May 2027 B.S. in Computer Science & Physics
Awards:
International Astronomy Olympiad (IAO): Overall Winner (2022); Gold (2022, 2021, 2019)
International Olympiad on Astronomy and Astrophysics (IOAA): Gold (2020); Silver (2022, 2021)
International Physics Olympiad (IPhO): Silver (2022); Bronze (2023)
European Physics Olympiad: Silver (2022, 2023)
Balkan Physics Olympiad: Gold (2022)
Relevant Experience:
Undergraduate Researcher, MIT Quantum Photonics & AI Group, Cambridge, MA, Feb 2024 – May 2024 Research Assistant,
Popmintchev Labs / Quantum Optics, University of California San Diego, San Diego, CA, Jul 2022 – Oct 2022
2026
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: The Fourteenth International Conference on Learning Representations (ICLR 2026)
2025
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)