2 papers
cs.LG2026
FNO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning
Fan Wu, Cheng Jing, Kookjin Lee
Neural operators enable fast PDE forecasting, but repeated predictions accumulate errors and fine-scale structures remain difficult to resolve. We introduce a frequency-decomposed…
cs.LG2026
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks
Cheng Jing, Abhishek Verma, Kallol Bera +2
Amortizing physics-informed neural networks (PINNs) across related PDEs requires describing each equation to a reusable solver. Coefficient vectors encode numerical parameters in p…