Floating-point neural networks with automatic differentiation can represent arbitrary floating-point functions and their gradients under mild conditions.
hub
Journal of Computational physics , volume=
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
fields
cs.LG 7 math.NA 2 cond-mat.mtrl-sci 1 cs.AI 1 cs.CE 1 cs.CV 1 cs.GR 1 cs.RO 1 eess.SY 1 physics.geo-ph 1years
2026 17roles
background 4polarities
background 4representative citing papers
McMg is a learned phase-space multi-channel multigrid preconditioner that maps residuals to corrections for heterogeneous Helmholtz equations and shows fewer iterations than classical and neural baselines in tests.
Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.
A hypernetwork conditions a conservative-form CNN to predict WENO5 weights from mesh and initial-condition metadata, preserving conservation and generalizing across resolutions for 1D hyperbolic conservation laws.
VHYDRO is a support-safe variational hybrid filter that jointly recovers continuous latent states, discrete contact modes, and sparse port-Hamiltonian laws per regime while preventing loss of feasible transitions.
Spatio-Temporal MeanFlow adapts MeanFlow to PDEs by replacing the generative velocity field with the physical operator and extending the integral constraint to the spatio-temporal domain, yielding a unified solver for time-dependent and stationary equations with improved accuracy and generalization.
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
A graph-based neural operator trained on expert-validated race-car CFD data reaches accuracy levels usable for early-stage interactive aerodynamic design exploration.
Paper-replication makes coding agents complete SciML paper replications only when every recorded claim has provenance, comparison evidence, and report coverage in a validated workspace.
SPLIT-PINN infers drift fields in Liouville transport equations from data using marginal corrections and orthogonality constraints to enable probabilistic predictions of microstructural evolution across polycrystal realizations.
StruMPL is a multi-task dense regression model that jointly addresses disjoint partial supervision, MNAR labels, and inter-task physical constraints for improved forest biomass estimation from Earth observation.
Geometric Pareto Control embeds Pareto solutions in a Lie group submanifold and navigates via Riemannian gradient flow to achieve 100% feasibility and low suboptimality in control tasks without retraining.
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
DiLaR-PINN learns dissipative effects in electromechanical systems via a skew-dissipative latent residual PINN that guarantees non-increasing energy and uses recurrent curriculum training for partial observations.
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
Physics-informed constraints on implicit neural representations yield more accurate and stable predictions of stirred-tank flows than purely data-driven models when training data is scarce, with diminishing returns at larger dataset sizes.
A reinforcement learning policy learns to adaptively harvest data samples, improving empirical constraint satisfaction and training efficiency for Lyapunov NNs and PINNs.
citing papers explorer
-
Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
Floating-point neural networks with automatic differentiation can represent arbitrary floating-point functions and their gradients under mild conditions.
-
McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation
McMg is a learned phase-space multi-channel multigrid preconditioner that maps residuals to corrections for heterogeneous Helmholtz equations and shows fewer iterations than classical and neural baselines in tests.
-
Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel
Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.
-
Hypernetwork-Conditioned WENO5 Conservative-Form CNNs for One-Dimensional Conservation Laws
A hypernetwork conditions a conservative-form CNN to predict WENO5 weights from mesh and initial-condition metadata, preserving conservation and generalizing across resolutions for 1D hyperbolic conservation laws.
-
Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery
VHYDRO is a support-safe variational hybrid filter that jointly recovers continuous latent states, discrete contact modes, and sparse port-Hamiltonian laws per regime while preventing loss of feasible transitions.
-
Physics-Informed Neural PDE Solvers via Spatio-Temporal MeanFlow
Spatio-Temporal MeanFlow adapts MeanFlow to PDEs by replacing the generative velocity field with the physical operator and extending the integral constraint to the spatio-temporal domain, yielding a unified solver for time-dependent and stationary equations with improved accuracy and generalization.
-
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
-
Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD
A graph-based neural operator trained on expert-validated race-car CFD data reaches accuracy levels usable for early-stage interactive aerodynamic design exploration.
-
Coding-agents can replicate scientific machine learning papers
Paper-replication makes coding agents complete SciML paper replications only when every recorded claim has provenance, comparison evidence, and report coverage in a validated workspace.
-
SPLIT-PINN: Separable Probability Learning Technique via Physics-Informed Neural Networks for High-Dimensional Probabilistic Modeling
SPLIT-PINN infers drift fields in Liouville transport equations from data using marginal corrections and orthogonality constraints to enable probabilistic predictions of microstructural evolution across polycrystal realizations.
-
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
StruMPL is a multi-task dense regression model that jointly addresses disjoint partial supervision, MNAR labels, and inter-task physical constraints for improved forest biomass estimation from Earth observation.
-
Geometric Pareto Control: Riemannian Gradient Flow of Energy Function via Lie Group Homotopy
Geometric Pareto Control embeds Pareto solutions in a Lie group submanifold and navigates via Riemannian gradient flow to achieve 100% feasibility and low suboptimality in control tasks without retraining.
-
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
-
Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems
DiLaR-PINN learns dissipative effects in electromechanical systems via a skew-dissipative latent residual PINN that guarantees non-increasing energy and uses recurrent curriculum training for partial observations.
-
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
-
Accelerated and data-efficient flow prediction in stirred tanks via physics-informed learning
Physics-informed constraints on implicit neural representations yield more accurate and stable predictions of stirred-tank flows than purely data-driven models when training data is scarce, with diminishing returns at larger dataset sizes.
-
Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints
A reinforcement learning policy learns to adaptively harvest data samples, improving empirical constraint satisfaction and training efficiency for Lyapunov NNs and PINNs.