Particle physics · machine learning · scientific computing
I am an experimental particle physicist at Northwestern University and Fermilab, and a convener of CMS Offline Samples. I develop physics-aware machine-learning methods, collider analyses, and reproducible tools for turning complex detector data into useful measurements.
Research portfolio · Google Scholar · CERN · Email
Finding structure in collisions—and in the data they leave behind.
- Collider measurements — analysis strategies for rare or structurally rich signatures, with interpretable observables and robust uncertainty treatment.
- Physics-aware machine learning — models that incorporate symmetry, geometry, and particle-interaction structure.
- Research infrastructure — reproducible generation, simulation, and analysis workflows that scale from notebooks to distributed computing.
| Project | Area | Links |
|---|---|---|
| CaloTrilogy | Physics-guided, end-to-end calorimeter shower generation | Preprint |
| Particle Transformer | Particle-interaction-aware attention for jet tagging | Paper · Code |
| State-space models for collider events | Efficient modeling of long, sparse particle sequences | Paper |
| Quantum models, made practical | Quantum kernels and knowledge distillation for collider physics | QNN study · CEPC application |
- higgs-combine-tool — an experimental route to a pip-installable CMS Combine v11.
- jetutor — matched JetClass editions for stress-testing taggers against generator choices.
- nano.rust — a semantics-first, pure-Rust framework for CMS NanoAOD analysis.
- DELPHI simulation pipeline — a bridge from modern HepMC3 generators to DELPHI simulation and reconstruction.
Explore the fuller research record, CMS analyses, appointments, and project notes at dickychant.github.io.