FreqNO-DPS corrects neural operator spectral bias in 3D elastic wavefield prediction by frequency-dependent guidance in diffusion posterior sampling conditioned on sparse observations, achieving near-zero bias at 2-5% sensor coverage.
A probabilistic framework for solving high-frequency helmholtz equations via diffusion models.arXiv preprint arXiv:2602.04082,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
APEX improves higher-frequency wave prediction under limited supervision by retaining amplitude anchors from coarse low-frequency extrapolations and reconstructing oscillatory detail via conditional flow-matching guided by Green's-function phase priors.
citing papers explorer
-
Correcting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations
FreqNO-DPS corrects neural operator spectral bias in 3D elastic wavefield prediction by frequency-dependent guidance in diffusion posterior sampling conditioned on sparse observations, achieving near-zero bias at 2-5% sensor coverage.
-
APEX: Amplitude Anchors and Phase Priors for Target-Scarce Higher-Frequency Wave Prediction
APEX improves higher-frequency wave prediction under limited supervision by retaining amplitude anchors from coarse low-frequency extrapolations and reconstructing oscillatory detail via conditional flow-matching guided by Green's-function phase priors.