AI Paper Atlas

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

Physics-Informed Residual Flows

Jephte Abijuru, Mayank Nagda, Phil Ostheimer, Sebastian Josef Vollmer, Marius Kloft, Sophie Fellenz

ICML 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training

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
Replace attention in PINNsFormer with a linear projection (ablation)PINNsFormer · Convection PDErMAE: 0.510 -> 0.012Improved
Replace attention in PINNsFormer with a shallow MLP (ablation)PINNsFormer · Wave PDErMAE: 0.270 -> 0.142Improved
Remove the SSM from PINNMamba (ablation)PINNMamba · Convection PDErMAE: 0.019 -> 0.012Improved
Replace SSM with parameter-matched MLP in PINNMamba (ablation)PINNMamba · Convection PDErMAE: 0.019 -> 0.063Hurt
Remove SSM from PINNMamba (ablation)PINNMamba · Reaction and Wave PDErMAE: 0.010 -> 0.013 (Reaction); 0.020 -> 0.029 (Wave)Hurt
Stack residual updates throughout the network (ResPINN) instead of one or two residual blocksPINN · Convection PDErMAE: 0.8514 -> 0.0028Improved
Use ResPINN instead of PirateNetHeat PDE · Heat PDErMAE: 0.0005 -> 0.0035Hurt
Use continuous-depth (O-PINN) instead of discrete ResPINN with wavelet activation (ablation)ResPINN · Reaction PDErMAE: 0.008 -> 0.003Improved
Use wavelet instead of tanh activation in ResPINN (ablation)ResPINN · Wave PDErMAE: 0.030 -> 0.070Hurt
Use wavelet instead of tanh activation in ResPINN (ablation)ResPINN · Convection PDErMAE: 0.015 -> 0.006Improved
Add residual connections after every two layers (same parameter count) (ablation)PINN · 1D convection Jacobian spectrumsingular valuesImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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