LiteRT.js runs machine learning models locally with CPU, GPU and emerging NPU acceleration, potentially reducing server infrastructure, inference charges and data movement.

This repository contains the code for LGNO, a Local--Global Neural Operator for learning one-step discrete flow maps for hyperbolic conservation laws. LGNO combines a global spectral branch with a ...

Abstract: Distributed computing is fundamental to multiagent systems, with solving distributed linear equations as a typical example. In this article, we study distributed solvers for network linear ...

Abstract: The future nonlinear equation system (FNES) problem requires obtaining the future solution by utilizing the current and past information. For industrial applications, such as real-time ...