The BSRA framework for dual sparse parameter efficient fine tuning with block structured gating and rank adaptation

Abstract Current large-scale language models face severe resource constraints when applied to downstream tasks. While full-fledged fine-tuning enhances model performance, it incurs substantial computational costs. Parameter-efficient fine-tuning (PEFT) techniques address resource limitations while m...

Description complète

Détails bibliographiques

Auteurs principaux:	Wang Jian, Guorong Chen, Hu Hong, Yixuan Zhang, Chongling Du, Zhang Bao
Format:	Artigo
Langue:	Inglês
Publié:	Nature Portfolio 2026-03-01
Collection:	Scientific Reports
Sujets:	Parameter-efficient fine-tuning Block-level structural sparsity Rank adaptation Dual sparsity
Accès en ligne:	https://doi.org/10.1038/s41598-026-40835-6
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!