AI RESEARCH
Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEs
arXiv CS.LG
•
ArXi:2605.24774v1 Announce Type: new We propose Hermite-NGP, a gradient-augmented multi-resolution hash encoding designed to enable fast and accurate computation of spatial derivatives for neural PDE solvers. Unlike existing NGP-based approaches that rely on automatic differentiation or finite differences and suffer from instability or high cost, Hermite-NGP explicitly s function values and mixed partial derivatives at hash grid vertices, allowing fully analytic evaluation of gradients, Jacobians, and Hessians via Hermite interpolation.