AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Test-Time Accuracy-Cost Control in Neural Simulators via Recurrent-Depth

Harris Abdul Majid, Pietro Sittoni, Francesco Tudisco

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and 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
add recurrent-depth (RecurrFNO 0.8B, 100 epochs) in place of a 1.6B FNOFNO · 3D Compressible Navier-Stokes (Density)MSE x10^-2: 7.61 -> 7.37Improved
use RecurrFNO 0.8B trained for 82 epochs against 1.6B FNOFNO · 3D Compressible Navier-Stokes (Pressure)MSE x10^-2: 7.59 -> 7.51Improved
replace ViT with RecurrViT using 58% of the parametersViT · Active Matter (Steps 0:3)MSE x10^-2: 2.91 -> 0.54Improved
replace ViT with RecurrViTViT · Active Matter (Steps 0:12)MSE x10^-2: 43.16 -> 5.68Improved
replace UPT with RecurrUPT (92M vs 164M parameters)UPT · ShapeNet-Car (32^3)MSE x10^-2: 2.31 -> 2.19Improved
increase backpropagation window from B=1 to B=2 (ablation)RecurrSim · Burgers (long-horizon, ~1M params)trajectory error (L2): 0.0849 -> 0.0315Improved
increase backpropagation window from B=2 to B=4 (ablation)RecurrSim · Korteweg-De Vries (long-horizon, ~1M params)trajectory error (L2): 0.0522 -> 0.0317Improved
increase backpropagation window from B=4 to B=32 (ablation)RecurrSim · Burgers (long-horizon, ~1M params)trajectory error (L2): 0.0199 -> 0.0178No clear effect
increase backpropagation window from B=4 to B=32 (ablation)RecurrSim · Kuramoto-Sivashinsky (long-horizon, ~1M params)trajectory error (L2): 1.3972 -> 1.3910No clear effect
increase mean training recurrent iterations K-bar beyond 32 (ablation)RecurrSim · Burgers, KdV, KSbest trajectory errorNo clear effect
train with larger K-bar (ablation)RecurrSim · Burgers, KdV, KStrajectory error at small KHurt
increase recurrent iterations K at test time up to 16 (Burgers) or 8 (KdV)RecurrFNO · Burgers and KdVtrajectory error (L2)Improved

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