AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

G-RANS: Generalizable Residual-Aware Neural Solvers for Sparse Systems

Weixin Liao, Mingquan Feng, Zhizhou Zhang, Youjia Wu, Yifan Fu, Junchi Yan

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers

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 multi-stage progressive bootstrap training (ablation)G-RANS · Poisson n≈1000 ±10%relative residual: 5.22e-4 -> 2.80e-5Improved
add multi-scale basis emission in the residual-aware basis generator (ablation)G-RANS · Poisson n≈1000 ±10%relative residual: 2.47e-2 -> 2.80e-5Improved
add both multi-scale and multi-stage (vs sub-NSS) (ablation)G-RANS · Poisson n≈1000 ±10%relative residual: 3.09e-2 -> 2.80e-5Improved
vary max active subspace dimension Kmax between 200 and 300 (ablation)G-RANS · G-RANSrelative residualNo clear effect
use G-RANS instead of end-to-end GNO/FNOG-RANS · n≈1000 FEM systemsrelative residual: GNO/FNO ~1e-2 to 1e-1 -> G-RANS 1e-5 levelImproved
increase coefficient variation from ±10% to ±70%G-RANS · Poisson n≈1000relative residual: 2.80e-05 -> 4.50e-05No clear effect
add Jacobi left preconditioning to G-RANS pipelineG-RANS · Helmholtz and React.-Diff.speedup over GMRES: 2.24x-2.26x with Jacobi vs about 3x withoutMixed
scale to 3D systems at n≈10^4G-RANS · Poisson-3Dspeedup over GMRES: 2.36x (n≈1000) -> 1.14x (n≈10000)Hurt
compare G-RANS wall-clock to GMRES/FGMRES at equal residualG-RANS · n≈1000 FEM systemsspeedup: 2-4xImproved

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