RepNN reparameterizes the first hidden layer of DNNs to enable adaptive frequency scaling, improving accuracy on oscillatory and multiscale functions with minimal extra cost.
Random weight factorization improves the training of continuous neural representations
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Oscillatory state-space models with PDE-aware spectral bases are introduced as inductive biases for PINNs, yielding improved accuracy and lower memory on forward, inverse, and up to 100D PDE tasks.
PINNACLE is an open-source framework for classical and quantum PINNs that supplies modular training methods and benchmarks showing high sensitivity to architecture choices plus parameter-efficiency gains in some hybrid quantum regimes.
PINN approach for time-domain Maxwell equations with split-field PMLs uses uniform equations across domains and matches analytical/FDTD results on 1D/2D Gaussian pulse tests.
citing papers explorer
-
RepNN: Tackling spectral bias in deep neural networks via parameter reparameterization
RepNN reparameterizes the first hidden layer of DNNs to enable adaptive frequency scaling, improving accuracy on oscillatory and multiscale functions with minimal extra cost.
-
Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
Oscillatory state-space models with PDE-aware spectral bases are introduced as inductive biases for PINNs, yielding improved accuracy and lower memory on forward, inverse, and up to 100D PDE tasks.
-
PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs
PINNACLE is an open-source framework for classical and quantum PINNs that supplies modular training methods and benchmarks showing high sensitivity to architecture choices plus parameter-efficiency gains in some hybrid quantum regimes.
-
Physics-Informed Neural Networks for the Time-Domain Maxwell Equations with Split-Field Perfectly Matched Layers
PINN approach for time-domain Maxwell equations with split-field PMLs uses uniform equations across domains and matches analytical/FDTD results on 1D/2D Gaussian pulse tests.