Menu

Research

Physics for AI, AI for Physics

Research Interests

Physics for AI

Physics Data for Understanding ML

Leveraging the unique properties of physics datasets (access to controllable data generation and known data symmetry and structure) to probe the internal mechanisms of deep neural networks.

Flow matching comparison
Figure from Generative Models on Phase Space
Physics for AI

Physics-Inspired Scaling Laws

Using an effective field theory to predict how neural network ensembles behave, deriving scaling laws for uncertainty quantification without the need to train an ensemble.

Scaling law predictions
Figure from Uncertainty Quantification from Ensemble Variance Scaling Laws in Deep Neural Networks
AI for Physics

AI for New Physics Search

Theory Parameter Estimation with Uncertainty Quantification, Simulation Emulation, and Automating the Search for Experimental Signatures.

Theory inversion via 2D density estimation
Figure from Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation. See also Searching for BSM Experimental Signatures with Large Lagrangian Models and its interactive blog, and ASTROLABE and its interactive blog.
AI for Physics

Foundation Models for Scientific Point Clouds

Building foundation models for scientific point clouds (irregular graphs!) that transfer knowledge across the domains of particle physics, cosmology, and molecular dynamics.

OmniMol energy predictions
Figure from OmniMol: Transferring Particle Physics Knowledge to Molecular Dynamics with Point-Edge Transformers. See also Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives.

All Publications

Physics for AI

  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. Generative Models on Phase Space
    Zachary Bogorad, Ibrahim Elsharkawy, et al.
    arXiv preprint, 2026
    arXiv
  3. Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives
    Ibrahim Elsharkawy, et al.
    arXiv preprint, 2026
    arXiv

AI for Physics

  1. Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
    Ibrahim Elsharkawy and Yonatan Kahn
    arXiv preprint, 2025
    arXiv
  2. OmniMol: Transferring Particle Physics Knowledge to Molecular Dynamics with Point-Edge Transformers
    Ibrahim Elsharkawy, et al.
    arXiv preprint, 2026
    arXiv
  3. FAIR Universe HiggsML Uncertainty Dataset and Competition
    Wahid Bhimji, et al.
    NeurIPS 2025, Dataset and Competition Track
  4. OmniCosmos: Transferring Particle Physics Knowledge across the Cosmos
    Vinicius Mikuni, et al.
    PRX Intelligence, 2026
    journal
  5. Searching for BSM Experimental Signatures with Large Lagrangian Models
    Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji, Aishik Ghosh
    arXiv preprint, 2026
    arXivInteractive Blog
  6. FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmology
    Biwei Dai, et al.
    Accepted to NeurIPS 2026
    arXiv
  7. ASTROLABE: A 3D Particle-Level Surrogate for Cosmology Simulation with Physical Flow Matching
    Ibrahim Elsharkawy, Yonatan Kahn, Neal Weiner, David Curtin
    arXiv preprint, 2026
    arXivInteractive Blog

Select Talks & Posters

Talks

Posters

Interested in collaborating?

Contact Me