Menu

About/CV Hi, I'm Ibrahim

A Quick Introduction

I am a PhD candidate at the University of Toronto advised by Prof. Yoni Kahn and doctoral researcher at Berkeley Lab (NERSC) advised by Wahid Bhimji and Benjamin Nachman. My research has been/is focused on using physics-inspired theory and physics data to understand neural network behavior, building foundation models that transfer across scientific domains, and developing AI tools to automate scientific discovery.

Education

  • 2025–Present

    PhD, Physics

    University of Toronto

  • 2023–2025

    MSc, Physics

    University of Illinois Urbana-Champaign

  • 2019–2023

    B.S., Computational Physics

    Rice University

  • 2019–2023

    B.A., Applied Mathematics & Philosophy

    Rice University

Experience

  • 2025–Present

    Doctoral Researcher

    Berkeley Lab

    Building foundation models for scientific point clouds/graphs for High Energy Physics, Cosmology and Molecular Dynamics at NERSC.

  • 2024–2025

    Research Geophysicist Intern

    ExxonMobil

    ML parameter estimation methods for 3D seismic inversion. Novel ML anomaly detection tools for 4D Seismic.

  • 2018–2023

    Research Geophysics & Software Intern

    Petroleum GeoServices

    ML methods for first break picking, seismic anomaly detection, cloud migration.

Awards

  • 2025 University of Toronto Connaught International Fellow
  • 2024 1st Place Higgs Uncertainty Challenge @ NeurIPS, CERN
  • 2023 3-Year UIUC Graduate College Fellowship
  • 2021 J & M Graham Physics Scholar
  • 2019 Shell Eco-Marathon
  • 2016 Eagle Scout

Teaching

  • 2026 TA and Lecturer, University of Toronto — Physics 2108/2109 “The Physics of Machine Learning”
  • 2025 TA, University of Toronto — Physics 252 “Thermal Physics”
  • 2024 TA, UIUC — Physics 413 “Optics Lab”

Select Papers

  1. Uncertainty Quantification from Ensemble Variance Scaling Laws in Deep Neural Networks
    Ibrahim Elsharkawy, et al.
    Machine Learning: Science and Technology, vol. 6, no. 3, 2025
    Paper
  2. Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
    Ibrahim Elsharkawy and Yonatan Kahn
    arXiv preprint, 2025
    arXiv
  3. OmniMol: Transferring Particle Physics Knowledge to Molecular Dynamics with Point-Edge Transformers
    Ibrahim Elsharkawy, et al.
    arXiv preprint, 2026
    arXiv
  4. FAIR Universe HiggsML Uncertainty Dataset and Competition
    Wahid Bhimji, et al.
    NeurIPS 2025, Dataset and Competition Track
  5. OmniCosmos: Transferring Particle Physics Knowledge across the Cosmos
    Vinicius Mikuni, et al.
    arXiv preprint, 2025
    arXiv

Select Talks & Posters

  • Invited Talk
    1st Place Competition Milestone (Ensembles and Uncertainty Quantification)
    The Challenge of Handling Uncertainties in Fundamental Science @ NeurIPS 2024
  • Invited Talk
    Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
    CERN 7th Inter-Experimental LHC Machine Learning Workshop, 2025
  • Poster
    FAIR Universe HiggsML Uncertainty Dataset and Competition
    NeurIPS 2025, Dataset and Competition Track
  • Poster
    Uncertainty Quantification from Scaling Laws in Deep Neural Networks
    Machine Learning and the Physical Sciences Workshop @ NeurIPS 2024
  • Poster
    Pre-Training For Science: A study on Foundation Model Training Objectives
    Stanford Center of Decoding the Universe Forum, 2025