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.
Guided diffusion sampling on function spaces with applications to pdes.arXiv preprint arXiv:2505.17004,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
DiLO turns diffusion sampling into deterministic latent optimization to satisfy the manifold consistency requirement for neural operators in inverse problem solving.
LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
Derives the conditional score exactly from an unconditional score via affine maps for linear inverse problems in infinite dimensions, shifting computation to offline training.
RecFM uses recursive self-consistency in flow matching to enable high-fidelity one- and few-step (2-4 step) generation of scientific dynamics, claiming 20x speedup over diffusion emulators and 15% lower MSE than vanilla flow matching.
LatentPDE reconstructs sparse scientific measurements by representing the latent space of a diffusion model as the coefficients and source terms of an assumed governing PDE.
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.
-
DiLO: Decoupling Generative Priors and Neural Operators via Diffusion Latent Optimization for Inverse Problems
DiLO turns diffusion sampling into deterministic latent optimization to satisfy the manifold consistency requirement for neural operators in inverse problem solving.
-
Latent Generative Solvers for Generalizable Long-Term Physics Simulation
LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
-
An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problems
Derives the conditional score exactly from an unconditional score via affine maps for linear inverse problems in infinite dimensions, shifting computation to offline training.
-
Recursive Flow Matching
RecFM uses recursive self-consistency in flow matching to enable high-fidelity one- and few-step (2-4 step) generation of scientific dynamics, claiming 20x speedup over diffusion emulators and 15% lower MSE than vanilla flow matching.
-
Learning Interpretable PDE Representations for Generative Reconstructions with Structured Sparsity
LatentPDE reconstructs sparse scientific measurements by representing the latent space of a diffusion model as the coefficients and source terms of an assumed governing PDE.