Umar Sohail Qureshi

Bio

I am a PhD student at Stanford University and a theoretical high-energy physicist in training, aiming to combine quantum field theory, novel experimental techniques, and machine learning to tackle fundamental questions in elementary physics.

My current research revolves around enhancing the discovery potential of the Large Hadron Collider and future colliders (such as the EIC, FCC, XCC, etc.) by developing novel theoretical approaches and data analysis methods.

In the past I have also dabbled with numerical relativitiy, condensed matter physics, geometric deep learning, optimal transport, and observational astronomy.

Conference Presentations

2025

Deep Image Reconstruction for Background Subraction in Heavy-ion Collisions.
Artificial Intelligence for the Electron Ion Collider (AI4EIC), MIT, Cambridge, MA, United States.

Model-Agnostic Tagging of Quenched Jets and Data-Driven Discovery of Quenching Observables in Heavy-ion Collisions.
Fall Meeting of the APS Division of Nuclear Physics (DNP), Chicago, IL, United States.

Deep Image Reconstruction for Background Subraction in Heavy-ion Collisions.
Machine Learning for Jet Physics (ML4Jets), California Institue of Technology, Pasadena, CA, United States.

Probing Stau-Neutralino Coannihilation at the High-Luminosity LHC through Vector Boson Fusion and Point Cloud Learning.
BOOST 2025: 17th International Workshop on Boosted Object Phenomenology, Reconstruction, Measurements, and Searches at Colliders, Brown University, Providence, RI, United States.

Probing a Quarkiophobic W' at the High-Luminosity LHC via Vector Boson Fusion and Lorentz Equivariant Point Cloud Learning.
The Phenomenology Symposium (Pheno), University of Pittsburgh, PA, United States.

Model-Agnostic Tagging of Quenched Jets in Heavy-ion Collisions.
Quark Matter: XXXI International Conference on Ultra-relativistic Nucleus-Nucleus Collisions, Goethe University, Frankfurt, Main, Germany.

PartonFlow: Reconstructing Parton-Level Jets after Hadronization.
Hot Jets: Advancing the Understanding of High Temperature QCD with Jets, Loomis Lab, Urbana Champaign, IL, United States.

2024

Generative Neural Networks for Reconstructing Parton-Level Jet Showers after Hadronization.
Machine Learning for Jet Physics (ML4Jets), LPNHE, Paris, France.

Probing the Supersymmetric Standard Model at the Large Hadron Collider through Vector Boson Fusion Processes and Machine Learning.
BOOST 2024: 16th International Workshop on Boosted Object Phenomenology, Reconstruction, Measurements, and Searches at Colliders, INFN, Genova, Italy.

Graph Neural Networks for Inverting Hadronization.
Fall Meeting of the APS Division of Nuclear Physics (DNP), MIT, Cambridge, MA.

A Herwig7 Underlying Event Tune for 200 GeV RHIC and EIC Energies.
Annual RHIC & AGS Users’ Meeting, Brookhaven National Lab, Upton, NY.

Probing a GeV-scale Scalar Boson and a TeV-scale Vector-like Quark in the U(1)T3R BSM Extension at the Large Hadron Collider using Machine Learning.
Phenomenology Symposium × APS Division of Particles & Fields (DPF) Meeting, University of Pittsburgh, PA.

2023

Probing a GeV-scale Scalar Boson in Association with a TeV-scale Vector-like Quark in the U(1)T3R BSM Extension at the LHC using Machine Learning.
31st International Symposium on Lepton Photon Interactions at High Energies, Monash University, Melbourne, Australia.

Probing a MeV-scale Scalar Boson and a TeV-Scale Vector-like Quark in the U(1)T3R BSM Extension from gg Fusion, qq Fusion at the LHC using Machine Learning.
XII International Conference on New Frontiers in Physics, Orthodox Academy of Crete, Greece.

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';