A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation
-
Updated
May 14, 2026
A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation
Graph neural network warm-start for AC power flow, ported from the RPF paper (arXiv:2601.09533).
Master's Thesis developed at Technische Universität München (TUM) under supervision of Prof. Stephan Günnemann.
A repository for training neural network models using Ordinary Differential Equations (ODEs) as the loss function. The project leverages JAX for efficient computation and Hydra for configuration management.
Add a description, image, and links to the neural-solver topic page so that developers can more easily learn about it.
To associate your repository with the neural-solver topic, visit your repo's landing page and select "manage topics."