PILIR mitigates spectral bias in PINNs by encoding explicit spatial locality via a learnable grid and synthesizing continuous fields with a generative neural operator, yielding higher accuracy on high-frequency PDE features.
Loss-attentional physics-informed neural networks.Journal of Computa- tional Physics, 501:112781
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PILIR: Physics-Informed Local Implicit Representation
PILIR mitigates spectral bias in PINNs by encoding explicit spatial locality via a learnable grid and synthesizing continuous fields with a generative neural operator, yielding higher accuracy on high-frequency PDE features.