AI Paper Atlas

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

TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs

Chen-Yang Dai, Che-Chia Chang, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai

ICML 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 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
replace time-as-input with time-induced parameters (TINN vs subMLP, same backbone, LM) (ablation)space-time PINN backbone · Burgersrelative L2 error: 7.11E-05 -> 6.89E-07Improved
replace time-as-input with time-induced parameters (TINN vs subMLP, same backbone, LM) (ablation)space-time PINN backbone · Allen-Cahnrelative L2 error: 1.76E-03 -> 3.85E-06Improved
use compact layer-wise time embedding instead of linear trajectory (ablation)TINN theta(t) · Burgersrelative L2 error: 2.65E-06 -> 5.67E-07Improved
use compact layer-wise time embedding instead of one-neuron trajectory (ablation)TINN theta(t) · Allen-Cahnrelative L2 error: 1.47E-05 -> 2.73E-06Improved
linear vs one-neuron trajectory for theta(t) (ablation)TINN theta(t) · Burgersrelative L2 error: 2.65E-06 vs 2.93E-06No clear effect
TINN time-induced parameterization instead of PirateNet, Adam training (ablation)TINN · Allen-Cahnrelative L2 error: 2.32E-03 -> 8.29E-05Improved
TINN trained with Adam instead of LM versus PirateNet (ablation)TINN · Burgersrelative L2 error: 2.43E-05 -> 2.15E-05No clear effect
layer-wise temporal embedding instead of naive HyperPINN-style hypernetwork (ablation)TINN · Klein-Gordonrelative L2 error: 2.02E-01 -> 4.78E-06Improved
layer-wise temporal embedding instead of naive HyperPINN-style hypernetwork (ablation)TINN · Allen-Cahnrelative L2 error: 3.49E-06 vs 3.85E-06No clear effect
time-induced parameterization instead of vanilla PINNTINN · Allen-Cahnrelative L2 error: 4.65E-01 -> 3.85E-06Improved
time-induced parameterization versus PirateNet SOAPTINN · Korteweg-De Vriesrelative L2 error: 4.26E-04 -> 1.53E-04Improved
time-induced parameterization versus CoPINN* on Klein-GordonTINN · Klein-Gordonrelative L2 error: 6.61E-06 -> 4.78E-06Improved

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