Arthur R. C. McCray

Stanford University

Stanford, CA

I’m a research scientist working at the intersection of machine learning and electron microscopy. I build self-supervised and physics-informed methods for inverse problems in scientific imaging, including deep generative priors, implicit neural representations, and differentiable forward models, and increasingly large pretrained models for materials data. Then I ship them as open-source tools that other microscopists can use.

Right now I’m building deep material priors: multimodal vision transformer foundation models for electron microscopy, pretrained at scale on simulated diffraction data together with crystal structure and composition. This is a $1.2M program with the Toyota Research Institute, and I led the technical contributions behind the award.

I’m a postdoctoral scholar in Colin Ophus’s group at Stanford University, after starting with the group at the National Center for Electron Microscopy at Berkeley Lab. There, I developed a self-supervised deep-prior framework for (S)TEM inverse problems. Applied to electron ptychography, it gives reconstructions more than 10× faster and with 40% higher resolution than state-of-the-art baselines, and it now underpins projects in ptychography, tomography, and crystallography. I also lead the ptychography and machine-learning development of quantEM, an open-source library for quantitative electron microscopy.

I did my Ph.D. in Applied Physics at Northwestern University and Argonne National Laboratory with Amanda Petford-Long and Charudatta Phatak. I used Lorentz transmission electron microscopy and computational methods to study magnetic skyrmions and other spin textures in van der Waals magnets. I also wrote PyLorentz, a Python package for Lorentz TEM simulation and phase reconstruction. Before that, I studied physics at Carleton College.

Want to learn more? Check out the interactive demos, which run electron microscopy simulations and reconstructions live in your browser.

selected publications

arXiv

Deep generative priors for robust and efficient electron ptychography

Arthur R. C. McCray, Stephanie M. Ribet, Georgios Varnavides, and 1 more author

arXiv preprint arXiv:2511.07795, 2025

arXiv Bib HTML Code

@article{mccray2025deep,
  title = {Deep generative priors for robust and efficient electron ptychography},
  author = {McCray, Arthur R. C. and Ribet, Stephanie M. and Varnavides, Georgios and Ophus, Colin},
  journal = {arXiv preprint arXiv:2511.07795},
  year = {2025},
}

J. Microsc.

Accelerating iterative ptychography with an integrated neural network

Arthur R. C. McCray, Stephanie M. Ribet, Georgios Varnavides, and 1 more author

Journal of Microscopy, 2025

DOI Bib HTML

@article{mccray2025accelerating,
  title = {Accelerating iterative ptychography with an integrated neural network},
  author = {McCray, Arthur R. C. and Ribet, Stephanie M. and Varnavides, Georgios and Ophus, Colin},
  journal = {Journal of Microscopy},
  volume = {300},
  number = {2},
  pages = {180--190},
  year = {2025},
  doi = {10.1111/jmi.13407},
}

APL ML

Simulation-trained machine learning models for Lorentz transmission electron microscopy

Arthur R. C. McCray, Alec Bender, Amanda Petford-Long, and 1 more author

APL Machine Learning, 2024

DOI Bib HTML

@article{mccray2024simulation,
  title = {Simulation-trained machine learning models for Lorentz transmission electron microscopy},
  author = {McCray, Arthur R. C. and Bender, Alec and Petford-Long, Amanda and Phatak, Charudatta},
  journal = {APL Machine Learning},
  volume = {2},
  number = {2},
  pages = {026120},
  year = {2024},
  doi = {10.1063/5.0197138},
}

npj Comput. Mater.

AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

Arthur R. C. McCray, Tao Zhou, Saugat Kandel, and 3 more authors

npj Computational Materials, 2024

DOI Bib HTML Code

@article{mccray2024ai,
  title = {AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures},
  author = {McCray, Arthur R. C. and Zhou, Tao and Kandel, Saugat and Petford-Long, Amanda and Cherukara, Mathew J. and Phatak, Charudatta},
  journal = {npj Computational Materials},
  volume = {10},
  pages = {111},
  year = {2024},
  doi = {10.1038/s41524-024-01285-8},
}

Nano Lett.

Thermal hysteresis and ordering behavior of magnetic skyrmion lattices

Arthur R. C. McCray^*, Yue Li^*, Rabindra Basnet, and 6 more authors

Nano Letters, 2022

DOI Bib HTML

@article{mccray2022thermal,
  title = {Thermal hysteresis and ordering behavior of magnetic skyrmion lattices},
  author = {McCray, Arthur R. C. and Li, Yue and Basnet, Rabindra and Pandey, Krishna and Hu, Jin and Phelan, Daniel P. and Ma, Xuedan and Petford-Long, Amanda K. and Phatak, Charudatta},
  journal = {Nano Letters},
  volume = {22},
  number = {19},
  pages = {7804--7810},
  year = {2022},
  doi = {10.1021/acs.nanolett.2c02275},
}

Phys. Rev. Appl.

Understanding complex magnetic spin textures with simulation-assisted Lorentz transmission electron microscopy

Arthur R. C. McCray, Tim Cote, Yue Li, and 2 more authors

Physical Review Applied, 2021

Editors’ Suggestion DOI Bib HTML Code

Selected as an Editors’ Suggestion in Physical Review Applied.

@article{mccray2021understanding,
  title = {Understanding complex magnetic spin textures with simulation-assisted Lorentz transmission electron microscopy},
  author = {McCray, Arthur R. C. and Cote, Tim and Li, Yue and Petford-Long, Amanda K. and Phatak, Charudatta},
  journal = {Physical Review Applied},
  volume = {15},
  number = {4},
  pages = {044025},
  year = {2021},
  doi = {10.1103/PhysRevApplied.15.044025},
}