Emil M. Constantinescu

Diff-NekRS: A Scalable Differentiable Framework for Multi-Timestep Solver-in-the-Loop Training

Diff-NekRS is introduced, a scalable differentiable framework that embeds neural corrections directly in the GPU-accelerated NekRS incompressible-flow solver, and establishes a verified and scalable path for multi-timestep solver-in-the-loop training that improves coarse-grid trajectory accuracy while retaining a speed...