An active learning method based on E-SINDy identifies governing ODEs and PDEs accurately with significantly fewer data samples than random sampling across tested systems.
hub
Query by committee
3 Pith papers cite this work, alongside 1,657 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1,657
external citations · external index
hub tools
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
OGAS uses a parallel diffusion model to bias PDE configuration sampling toward high surrogate difficulty, reducing 99th-percentile errors and error variance versus uniform sampling across tested 2D PDEs.
ARC-STAR reduces velocity rollout error by at least 36x over raw Poseidon across all tested regime cells via auditable global and local correction stages on five flow benchmarks.
citing papers explorer
-
How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit
An active learning method based on E-SINDy identifies governing ODEs and PDEs accurately with significantly fewer data samples than random sampling across tested systems.
-
Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
OGAS uses a parallel diffusion model to bias PDE configuration sampling toward high surrogate difficulty, reducing 99th-percentile errors and error variance versus uniform sampling across tested 2D PDEs.
-
ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
ARC-STAR reduces velocity rollout error by at least 36x over raw Poseidon across all tested regime cells via auditable global and local correction stages on five flow benchmarks.