Machine learning for high-energy physics, collider inference, and physics beyond the Standard Model.
My research is driven by fundamental questions in high-energy physics: the mechanism of electroweak symmetry breaking, the search for physics beyond the Standard Model, and the extraction of maximal information from collider data.
To address these questions, I develop machine-learning methods that improve the precision, computational efficiency, and robustness of collider analyses, with applications to jet physics, collider phenomenology, simulation-based inference, and generative models for fast event generation.
Systematics-aware collider inference
I work on machine-learning-based statistical inference methods for collider physics, including both binned and unbinned analyses. My focus is on simulation-based inference and likelihood-based measurements that incorporate systematic uncertainties directly into the inference procedure, enabling more robust use of high-dimensional collider observables.
Machine learning for jet physics
I develop neural architectures and physics-motivated representation-learning methods for jet tagging, quark/gluon discrimination, boosted-object identification, and jet-substructure studies. This includes working with diverse jet representations such as high-level physics-inspired features, jet images, point clouds, graph-based inputs, and sequence-based architectures.
Efficient machine learning for particle physics
I am interested in the limits of compact and low-precision neural networks for high-energy physics analyses, including how far model compression can be pushed without losing physics performance.
Collider phenomenology and new physics searches
I study collider signatures of physics beyond the Standard Model, including extended Higgs sectors, axion-like particles, dark-sector candidates, and machine-learning-assisted search strategies at the LHC and future colliders.
Looking ahead, I am particularly interested in foundation-model architectures for collider physics and principled uncertainty quantification in machine-learning-based inference.