AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Test-time Generalization for Physics through Neural Operator Splitting

Louis Serrano, Jiequn Han, Edouard Oyallon, Shirley Ho, Rudy Morel

ICML 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural operators for general geometries · 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
add test-time beam search over operator compositions with operator splittingDISCO · Unseen PDE combination: Advection+DiffusionNRMSE: 0.170 -> 0.015Improved
add test-time beam search over operator compositionsDISCO · Unseen PDE combination: Euler+DiffusionNRMSE: 0.572 -> 0.066Improved
use beam search instead of uniform sampling to pick operatorsoperator composition search · Unseen PDE combination: All ThreeNRMSE: 0.075 -> 0.036Improved
use beam search instead of uniform samplingoperator composition search · Unseen PDE combination: Nonlinear Adv.+DiffusionNRMSE: 0.068 -> 0.056Improved
add test-time beam searchDISCO · Parameter extrapolation: Adv.-Diff. DNRMSE: 0.159 -> 0.002Improved
add test-time beam searchDISCO · Parameter extrapolation: Combined gammaNRMSE: 1.007 -> 0.022Improved
add test-time beam searchDISCO · Parameter extrapolation: Adv.-Diff. cNRMSE: 0.768 -> 0.052Improved
increase number of uniform-search trials (ablation)uniform search · OOD advection-diffusionfitting and prediction NRMSEImproved
increase dictionary size from 64 to 256 under Mixed 0.5 training (ablation)beam search · Mixed-physics training (Mixed 0.5)NRMSE improvement over direct: 0% -> 41%Improved
increase dictionary size from 64 to 256 under Mixed 1.0 training (ablation)beam search · Mixed-physics training (Mixed 1.0)NRMSE improvement over direct: 15% -> 32%Improved
increase unseen nonlinear perturbation eps from 0 to 1.00 (ablation)beam search · Adv-Diff with Burgers perturbationBeam NRMSE: 0.055 -> 0.797Hurt
improve accuracy of individual learned operators via longer pretraining (epoch 50 to 500) (ablation)Strang splitting of heat and dispersion operators · 1D heat-dispersionSplit Rollout NRMSE: 1.22e-01 -> 8.85e-03Improved

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