The site is under construction — sorry for the (temporarily) limited information.
I am a postdoctoral researcher at CEITEC with interests in technical AI safety, security, and the science of deep learning. I hold a PhD in applied physics and have worked on interpretable machine learning for spectroscopy as well as foundational aspects of deep learning. I also collaborate with KASL and was previously a visiting Ph.D. student at the University of Cambridge, advised by David Krueger.
My current research focuses on foundational topics in machine learning — loss-landscape geometry, parameter-space symmetries, mode connectivity, and overparameterization — with the broader aim of advancing AI security and safety. I combine empirical and theoretical approaches, often grounded in physics, to better understand deep learning and improve its interpretability and robustness.
When I'm not busy with ML experiments, you can find me bouldering or cycling. I also enjoy hiking, playing guitar, and reading physics books from my vast collection.
News
- Jul 2026Joining CST, University of Cambridge, as a postdoctoral research associate.
- Oct 2025Gave a talk on Mode Connectivity for AI Security & Safety at the Oxford AI Safety Initiative's technical roundtable seminar.
- Jul 2025Joining the Artificial Intelligence Governance Initiative (AIGI) at the University of Oxford as a Visiting Research Fellow for three months, working on automated interpretability (with Fazl Barez).
- Jan 2025Input space mode connectivity was accepted to ICLR 2025.
- Oct 2024Input space mode connectivity accepted for an oral presentation at SciForDL at NeurIPS 2024.
- Aug 2024Attending the IAIFI summer school and workshop at MIT, giving a talk on input space mode connectivity.
- Jun 2024Visiting KASL ⊂ CBL, University of Cambridge, for four months.
- May 2024At the Youth in High Dimensions workshop at ICTP in Trieste, Italy.
Research interests
- Machine learning foundations
- overparametrization, double descent, NTK
- loss-landscape symmetries, mode connectivity
- sparsity, lottery tickets
- ANN interpretability (for spectroscopic data)
- feature visualization, optimal manifold
- sparsity for (mechanistic) interpretability
- custom loss penalization
- AI safety
- LLM jailbreaking (defenses)
Current projects
Input space mode connectivity
We generalized the concept of loss-landscape mode connectivity to the input space of deep neural networks.
Sparse, interpretable ANNs for spectroscopic data
We study custom loss penalization for MLPs that leads to interpretable and spectroscopically relevant weights in the first layer.
Lottery tickets vs. double descent
A solo project studying intrinsic limitations of lottery-ticket performance as it depends on the initial effective complexity.
