Cód QR

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...

Cur síos iomlán

Sábháilte in:
Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Wang Jian, Guorong Chen, Hu Hong, Yixuan Zhang, Chongling Du, Zhang Bao
Formáid: Artigo
Teanga:Inglês
Foilsithe / Cruthaithe: Nature Portfolio 2026-03-01
Sraith:Scientific Reports
Ábhair:
Rochtain ar líne:https://doi.org/10.1038/s41598-026-40835-6
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!