IEEE

WireLightning: Harnessing Capacitances for In-Transit Massively Parallel Matrix Multiplication

Abstract: Analog computing-in-memory accelerators promise ultra-low-power, on-device AI by reducing data transfer and energy usage. Yet inherent device variations and high energy consumption for ...
IEEE

DLRNMFMDA: miRNA-Disease Associations Prediction Method Based on Dual Laplacian Regularized Non-Negative Matrix Factorization

Abstract: microRNAs (miRNAs) represent a class of non-coding RNAs intricately linked to numerous biological processes and human diseases. Traditional biological methods for identifying miRNA-disease ...
GitHub

QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models

QiMeng-GEMM is an innovative approach to automatically generate high-performance matrix multiplication (GEMM) code using LLMs. This codebase provides a comprehensive solution for efficiently computing ...
GitHub

EDGES is a spatially constrained non-negative matrix factorization (NMF) framework designed for gene expression denoising and prediction in spatial transcriptomic (ST) data.

X: shared genes by cells matrix of ST data. Y: shared genes by cells matrix of scRNA-seq data. Z: unique genes by cells matrix of scRNA-seq data. L1: cells by cells matrix. A precomputed normalized ...
Healio

Headline News

HUNTINGTON BEACH, Calif. — Avoiding unplanned pregnancies in rheumatology patients can limit trauma and help steer clear of the labyrinth of U.S. abortion laws, according to a speaker at the 2025 ...
PNAS

Origami frustration and its influence on energy landscapes of origami assemblies

Frustration: detrimental or desirable? Sometimes detrimental, but sometimes desirable to achieve new functionalities of nonrigid multistable origami structures. It provides the means to augment the ...