Research

Journal and Conference Papers

[3] L. J. Shikhman. One Operator to Rule Them All? On Boundary-Indexed Operator Families in Neural PDE Solvers. ICLR 2026 Workshop on AI & Partial Differential Equations, under review.

[2] L. J. Shikhman. Forcing and Diagnosing Failure Modes of Fourier Neural Operators Across Classes of PDEs. Transactions on Machine Learning Research, under review. [arXiv] [code]

[1] L. J. Shikhman. Entropy Production in Machine Learning Under Fokker–Planck Probability Flow. Transactions on Machine Learning Research under review. [arXiv]

Invited Talks

[1] L. J. Shikhman, L. Lawler. Deploying Physics Models at the Edge: Quantized AI for Weather and Fluid Simulation on Dell Pro Max with GB10. Optimized AI Conference, 2026, Atlanta, GA.

Manuscripts in Preparation

L. J. Shikhman, N. Welsh, R. White, M. Nguyen. Open-Set Localization of Spacecraft Components from On-Orbit Imagery Using Vision-Language Models.

L. J. Shikhman, T. Ploetz, S. G. Dhekane. Manifold Learning for Early Detection of Influenza-like Illness from Wearable Data.

B. Buchwald, L. J. Shikhman, B. Gisclair, N. Welsh, R.T. White, R.J. Usselman. Hyperspectral Single-Shot Autofocus via Frequency-Domain Voting

L. Papadopoulos, E. Reck, L. J. Shikhman. Accounting-Informed Machine Learning for Detecting Financial Reporting Fraud.