3 papers
cs.LG2026
Physics-informed fine-tuning of foundation models for partial differential equations
Vlad Medvedev, Leon Armbruster, Christopher Straub +2
Foundation models for partial differential equations (PDEs) have emerged as powerful surrogates pre-trained on diverse physical systems, but adapting them to new downstream tasks r…
physics.optics2025
Physics-Informed PointNets for Modeling Electromagnetic Scattering from All-Dielectric Metasurfaces with Inclined Nanopillars
Leon Armbruster, Vlad Medvedev, Andreas Rosskopf
Metasurfaces are innovative planar optical structures capable of manipulating incident light properties. Accurate and computationally efficient modeling of such metasurfaces, parti…
cs.LG2025
Hard-constraining Neumann boundary conditions in physics-informed neural networks via Fourier feature embeddings
Christopher Straub, Philipp Brendel, Vlad Medvedev +1
We present a novel approach to hard-constrain Neumann boundary conditions in physics-informed neural networks (PINNs) using Fourier feature embeddings. Neumann boundary conditions…