A jet grooming algorithm based on reinforcement learning.

Generative models for jet substructure.

A set of python-based Monte Carlo tools for jet physics, including Monte Carlo integration, parton showering, and examples.

CycleGan for jet substructure.

Scripts and notebooks for pre-processing jet data into different formats, primarily the jet-image and Lund plane formats. The focus is on datasets used in the Landscape of Top Taggers challenge.

Code to use the Latent Dirichlet Allocation probabilistic model to extract sub-classes (topics) from collider data.

Scripts and notebooks for pre-processing di-jet event data into different formats, primarily the jet-image and Lund plane formats. The focus is on the LHC Olympics 2020 datasets.

Classifying hadronic tau jets vs light quark jets using CNNs and jet images from e+e- collisions. Includes full simulation pipeline (MadGraph, Pythia8, FastJet) and model evaluation across energies for tau-tagging performance.

Jet Energy Corrections with Graph Neural Network Regression

Jet Energy Calibration with Deep Learning as a Kubeflow Pipeline

Este código de Python implementa algoritmos para describir distribuciones de Maxwell-Jütnner estacionarias y desplazadas, y su aplicación en el modelo de un sistema de transporte de jets relativistas en un medio intergaláctico magnetizado, por medio de un esquema tipo particle-in-cell (PIC).