Saved in:
Bibliographic Details
Main Authors: Faroughy, Darius A., Opper, Manfred, Ojeda, Cesar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.01736
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918214287491072
author Faroughy, Darius A.
Opper, Manfred
Ojeda, Cesar
author_facet Faroughy, Darius A.
Opper, Manfred
Ojeda, Cesar
contents Generative modeling of high-energy collisions at the Large Hadron Collider (LHC) offers a data-driven route to simulations, anomaly detection, among other applications. A central challenge lies in the hybrid nature of particle-cloud data: each particle carries continuous kinematic features and discrete quantum numbers such as charge and flavor. We introduce a transformer-based multimodal flow that extends flow-matching with a continuous-time Markov jump bridge to jointly model LHC jets with both modalities. Trained on CMS Open Data, our model can generate high fidelity jets with realistic kinematics, jet substructure and flavor composition.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Generative Flows for LHC Jets
Faroughy, Darius A.
Opper, Manfred
Ojeda, Cesar
High Energy Physics - Phenomenology
Machine Learning
Generative modeling of high-energy collisions at the Large Hadron Collider (LHC) offers a data-driven route to simulations, anomaly detection, among other applications. A central challenge lies in the hybrid nature of particle-cloud data: each particle carries continuous kinematic features and discrete quantum numbers such as charge and flavor. We introduce a transformer-based multimodal flow that extends flow-matching with a continuous-time Markov jump bridge to jointly model LHC jets with both modalities. Trained on CMS Open Data, our model can generate high fidelity jets with realistic kinematics, jet substructure and flavor composition.
title Multimodal Generative Flows for LHC Jets
topic High Energy Physics - Phenomenology
Machine Learning
url https://arxiv.org/abs/2509.01736