Results 171 to 180 of about 1,750,538 (276)
A hybrid re-fusion model for text classification. [PDF]
Liu Q, Xiao K, Qian Z.
europepmc +1 more source
Screen gate‐based transistors are presented, enabling tunable analog sigmoid and Gaussian activations. The SA‐transistor improves MRI classification accuracy, while the GA‐transistor supports precise Gaussian kernel tuning for forecasting. Both functions are implemented in a single device, offering compact, energy‐efficient analog AI processing ...
Junhyung Cho +9 more
wiley +1 more source
Hierarchical contrastive learning for multi-label text classification. [PDF]
Zhang W, Jiang Y, Fang Y, Pan S.
europepmc +1 more source
Directional Flow of Confined Polaritons in CrSBr
CrSBr, a layered magnetic semiconductor, naturally channels self‐hybridized excitonpolaritons into highly directional flow. Its intrinsic optical anisotropy, high refractive index, and strong lightmatter coupling enable long‐range guided modes along the a‐axis, with propagation lengths set by their excitonphoton admixture.
Pratap Chandra Adak +10 more
wiley +1 more source
Parameter-efficient fine-tuning for low-resource text classification: a comparative study of LoRA, IA<sup>3</sup>, and ReFT. [PDF]
Nwaiwu S.
europepmc +1 more source
Intelligent Acousto‐Electrical Metamaterials (IAM) for Sound Source Detection
Our proposed metamaterial concept enables sound source detection using a single material, in contrast to conventional arrays that require dozens or even hundreds of transducers. We show that the coupled acoustic–vibrational–electrical responses in piezoelectric metamaterials give rise to topology‐governed charge transport, producing distinct voltage ...
Victor Couëdel +7 more
wiley +1 more source
Adaptive feature interaction enhancement network for text classification. [PDF]
Su R, Gao S, Zhao K, Zhang J.
europepmc +1 more source
Magnetic tunnel junctions (MTJs) using MgO tunnel barriers face challenges of high resistance‐area product and low tunnel magnetoresistance (TMR). To discover alternative materials, Literature Enhanced Ab initio Discovery (LEAD) is developed. The LEAD‐predicted materials are theoretically evaluated, showing that MTJs with dusting of ScN or TiN on ...
Sabiq Islam +6 more
wiley +1 more source

