This paper introduces Sirens, neural networks with periodic activation functions for implicit neural representations. The approach enables modeling of complex signals and their derivatives, solving partial differential equations like Eikonal, Poisson, and wave equations, with applications across images, video, sound, and wavefields.
LinearSolveBench is a new benchmark designed to advance algorithms for solving large sparse linear systems and to measure AI models' ability to discover such algorithms. It includes 9,984–113,664 row matrices from FLASH magnetic-diffusion problems and spans applications across power grids, fusion energy, quantitative finance, structural mechanics, and fluid dynamics.