AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Revisiting Neural Processes via Fourier Transform and Volterra Series

Peiman Mohseni, Nick Duffield, Raymond K. W. Wong

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neuro-symbolic probabilistic layers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SFConvCNP instead of attention-based models on sawtoothCNP family · Synthetic 1D Sawtoothlog-likelihood: -0.87 -> 1.19Improved
replace pointwise non-linearities with identity in baseline backbones (ablation)TNP, TE-TNP, AttnCNP baselines · Synthetic 1D regressionlog-likelihoodHurt
remove pointwise non-linearities from SFConvCNP backbone (ablation)SFConvCNP · Synthetic 1D regressionlog-likelihoodNo clear effect
use SFConv-based models instead of non-equivariant CNP when shifting regionERA5 regression · ERA5 Western Europe (OOD)log-likelihood: <-10 -> 1.71Improved
use Volterra construction (SFVConvCNP) instead of stacked SFConv blocksSFConvCNP · Kolmogorov flowlog-likelihood: 1.89 -> 1.48Hurt
use Volterra construction (SFVConvCNP) instead of stacked SFConv blocksSFConvCNP · ERA5 Central Europe (ID)log-likelihood: 1.55 -> 1.09Hurt
use Volterra construction (SFVConvCNP) instead of stacked SFConv blocksSFConvCNP · Synthetic 1D Squarelog-likelihood: -0.36 -> -0.10Improved
use SFConvCNP instead of grid-based SConvCNPGrid-SConvCNP · CIFAR-10 image completionlog-likelihood: 1.71 -> 1.74Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy