Physicist &
ML Researcher
PhD candidate studying generative models for physical systems and building foundation models for science.
University of Toronto, Vector Institute, Berkeley Lab (NERSC)
PhD advised by Yoni Kahn, committee: David Curtin & Chris Maddison
NERSC advised by Wahid Bhimji, Benjamin Nachman, Aishik Ghosh
Physics for AI, AI for Physics.
- Jun 2026NERSC AI4Sci proposal accepted: 7,000 GPU node-hours awarded
- Jun 2026FAIR Universe Weak Lensing Challenge accepted to NeurIPS 2026
- Jun 2026Released Pre-Training for Simulation-Based Science · talks at Vector & Stanford
- Apr 2026Awarded the NSERC Doctoral Scholarship (CGRS-D)
- Feb 2026Guest lecturer, “The Physics of Machine Learning” at U of T
- Jan 2026Released the OmniMol & OmniCosmos preprints
- Sep 2025First-place prize (ex aequo) at CERN · HiggsML Uncertainty Challenge, NeurIPS 2025
- May 2025Released Contrastive Normalizing Flows · invited talks at MIT IAIFI & Berkeley Lab
- Mar 2025Awarded the U of T Connaught International Fellowship
- Dec 2024Invited talk on the first-place Higgs solution at NeurIPS 2024 · Milestone award
Select Papers
-
arXiv preprint, 2026
-
arXiv preprint, 2026
-
The Omni family: cross-domain scientific foundation modelsTransferring particle-physics knowledge to molecular dynamics and cosmology.
-
arXiv preprint, 2025
Research Focus
Physics Data for Understanding ML
Leveraging the controllable generation and known symmetries of physics datasets to probe the internal mechanisms of deep neural networks.
Physics-Inspired Theory for Scaling Laws
Using effective field theory to predict neural-network ensemble behavior and derive uncertainty scaling laws without training an ensemble.
Automating Scientific Model Building
Developing ML for “theory inversion”: parameter estimation with uncertainty quantification, simulation emulation, and automated theory writing.
Cross-Domain Foundation Models
Foundation models for scientific point clouds that transfer knowledge across particle physics, cosmology, and molecular dynamics.
