LoRA meets dropout under a unified framework
Aug 1, 2024·
,,,,·
0 min read
Sheng Wang
Equal contribution
,Liheng Chen
Jiyue Jiang
Boyang Xue
Lingpeng Kong
Chuan Wu
Abstract
This paper presents a unified framework connecting LoRA and dropout, providing theoretical insights and practical improvements for parameter-efficient fine-tuning.
Type
Publication
In Findings of the Association for Computational Linguistics ACL 2024
Authors
Sheng Wang
(Forence)
PhD Graduate in Computer Science
Sheng Wang is a PhD graduate from The University of Hong Kong, supervised by Prof. Chuan Wu and Prof. Lingpeng Kong.
His research focuses on Agent, LLM Super-Alignment, and Data Synthesis. He has published 14+ papers in top-tier
conferences including NIPS2025 (Spotlight), ICLR2025, ACL2024/2025, EMNLP2025.
Authors
Authors
Authors
Authors
Authors