Results 1 to 10 of about 1,727 (160)

KnitLoRA: bridging low-rank adaptation as interwoven layers for deeper semantic reasoning [PDF]

Scientific Reports
Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method that facilitates the lightweight adaptation of large language models (LLMs) by introducing low-rank update matrices, and has since motivated the development of various ...
Hongjie Qiu, Youyou Ning, Jinqiang Li, Xiangrong Zhu, Yifan Gong, Liqi Yan, Fangli Guan, Jianhui Zhang, Fuli Feng, Zenglin Xu, Qifan Wang, Pan Li   +11 more
doaj   +2 more sources

High-accuracy ECG image interpretation using parameter-efficient Low-Rank Adaptation (LoRA) fine-tuning with multimodal LLaMA V.3.2 [PDF]

BMJ Digital Health & AI
Objective To develop and evaluate a high-accuracy ECG image interpretation model using parameter-efficient Low-Rank Adaptation (LoRA) fine-tuning with the multimodal LLaMA V.3.2 model.Methods and analysis We fine-tuned the multimodal LLaMA V.3.2 model ...
Nandakishor Mukkunnoth, Anjali Mukkunnoth, Meenakshi Khapre, Sudarshan Benamanahalli Puttaswamy   +3 more
doaj   +2 more sources

Parameter-Efficient LoRA-GRL Adaptation for Cross-Center Classification of Benign and Malignant Lung Nodules on Heterogeneous Standard-Dose Chest CT: A Multi-Institutional Study from Palestine [PDF]

Journal of Imaging
Automated CT lung nodule classification suffers from domain shift across centers. We propose LoRA-GRL, combining Low-Rank Adaptation (LoRA) with adversarial domain harmonization via a Gradient Reversal Layer.
Radwan Qasrawi, Razan AbuGhoush, Ghada Issa, Suliman Thwib, Malak Amro, Rand Al Taweel, Sara Asfour, Yazan Dibas, Tawfiq Abukeshek, Marwan Qubja   +9 more
doaj   +2 more sources

Evaluating the efficiency and factual reliability of LoRA for health misinformation detection [PDF]

Scientific Reports
This research investigates the effectiveness and reliability of Low-Rank Adaptation (LoRA) for detecting health misinformation. While parameter-efficient fine-tuning (PEFT) methods reduce computational costs significantly, their impact on model ...
Yiping Li, Xuanfeng Li, Mark Ching-Pong Poo, Yuejing Zhai, Leila Kamalian, Chitin Hon, Di Wang   +6 more
doaj   +2 more sources

DC-LoRA: Domain correlation low-rank adaptation for domain incremental learning

High-Confidence Computing
Continual learning, characterized by the sequential acquisition of multiple tasks, has emerged as a prominent challenge in deep learning. During the process of continual learning, deep neural networks experience a phenomenon known as catastrophic ...
Lin Li, Shiye Wang, Changsheng Li, Ye Yuan, Guoren Wang   +4 more
doaj   +3 more sources

From LLM to FEM: Low-Rank Adaptation for Noise-Robust Structural Damage Detection [PDF]

Sensors
Structural damage detection using the finite element method is inherently formulated as an inverse problem, often suffering from ill-posedness and high sensitivity to measurement noise.
Jaedong Kim, Haesu Kang, Sungyong Chang
doaj   +2 more sources

Structure-Aware Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Mathematics, 2023
With the growing scale of pre-trained language models (PLMs), full parameter fine-tuning becomes prohibitively expensive and practically infeasible.
Yahao Hu, Yifei Xie, Tianfeng Wang, Man Chen, Zhisong Pan   +4 more
doaj   +1 more source

LoRA: Low-Rank Adaptation of Large Language Models

CoRR, 2021
Draft V2 includes better baselines, experiments on GLUE, and more on adapter ...
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen   +7 more
openaire   +3 more sources

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

CoRR, 2023
Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden largely restricts the application of LLMs especially when one needs to deploy them onto edge devices.
Yuhui Xu 0002, Lingxi Xie, Xiaotao Gu, Xin Chen 0033, Heng Chang, Hengheng Zhang, Zhengsu Chen, Xiaopeng Zhang 0008, Qi Tian 0001   +8 more
openaire   +3 more sources

LoRA-GA: Low-Rank Adaptation with Gradient Approximation

Advances in Neural Information Processing Systems 37
Fine-tuning large-scale pretrained models is prohibitively expensive in terms of computational and memory costs. LoRA, as one of the most popular Parameter-Efficient Fine-Tuning (PEFT) methods, offers a cost-effective alternative by fine-tuning an auxiliary low-rank model that has significantly fewer parameters.
Shaowen Wang 0002, Linxi Yu, Jian Li
openaire   +4 more sources