3 papers
cs.LG2026
RepNN: Tackling spectral bias in deep neural networks via parameter reparameterization
Yong Wang, Tao Zhou, Xuhui Meng
Deep neural networks (DNNs) have achieved remarkable success in scientific computing, yet they often suffer from spectral bias in capturing oscillatory and multiscale behaviors. In…
physics.comp-ph2026
Flow-based generative models for amortized Bayesian inference in regression and inverse PDE problems
Shaoqian Zhou, Ling Guo, Xuhui Meng
Bayesian inference provides a principled framework for uncertainty quantification in scientific machine learning. However, conventional Bayesian approaches usually require solving…
physics.flu-dyn2024
NeDF: neural deflection fields for sparse-view tomographic background oriented Schlieren
Jiawei Li, Xuhui Meng, Yuan Xiong +3
Three-dimensional (3D) density-varying turbulent flows are widely encountered in high-speed aerodynamics, combustion, and heterogeneous mixing processes. Multi-camera-based tomogra…