← Papers

Emulator superiority

When machine learning for PDEs surpasses its training data

Paper title Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data

Koehler and Thuerey

Paper arXiv 2510.23111PDF

Shows that emulators trained only on a low-fidelity solver can be more accurate than that solver against a higher-fidelity reference, and explains why through inductive biases and error accumulation in rollouts.

Published
NeurIPS

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. PhysicsNeMo-Mesh — GPU-Native Meshes and Simulation Cases for Physics AI
  2. Multi-fidelity scaling — Compute-optimal data scaling via multi-fidelity training
  3. CAE-UQ — Predictive Uncertainty for Neural CAE Surrogates