Results 141 to 150 of about 9,649,421 (248)

ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models [PDF]

Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in the era of large language models. Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular and representative method.
Zhu, Wei, Liu, Zequan, Lyn, Jiawen, Tian, Xing, Graham, Yvette   +4 more
core   +1 more source

Accelerating Stroke MRI With Diffusion Probabilistic Models Through Large‐Scale Pre‐Training and Target‐Specific Fine‐Tuning

Magnetic Resonance in Medicine, Volume 96, Issue 5, Page 2396-2411, November 2026.
ABSTRACT Purpose To develop a data‐efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables faster scan times in clinical stroke MRI when only limited fully‐sampled data are available. Methods Our simple training strategy first pre‐trains a DPM on a large, diverse collection of publicly ...
Yamin Arefeen, Sidharth Kumar, Steven Warach, Hamidreza Saber, Jonathan Isaac Tamir   +4 more
wiley   +1 more source

ArGemma: A Multi‐Task Fine‐Tuning Framework for Adapting Gemma to Arabic

Expert Systems, Volume 43, Issue 11, November 2026.
ABSTRACT Open‐source large language models (LLMs) have significantly advanced natural language processing (NLP), particularly for English. However, their performance in Arabic has remained limited due to the scarcity of high‐quality datasets and the high computational cost of full fine‐tuning.
Taha Alselwi, Serap Çakar Kaman, Beyza Eken   +2 more
wiley   +1 more source

Large Language Models and Agentic AI for Vulnerability Management: A Systematic Review

Expert Systems, Volume 43, Issue 11, November 2026.
ABSTRACT Large Language Models (LLMs), pretrained language and code models and agentic artificial intelligence are increasingly being investigated across the vulnerability‐management lifecycle. However, the evidence remains fragmented across code‐level prediction, vulnerability‐intelligence enrichment, exploit‐oriented evaluation, automated repair and ...
Yasamin Akrami, Malek Malkawi, Reda Alhajj   +2 more
wiley   +1 more source

SBoRA: Low-Rank Adaptation with Regional Weight Updates [PDF]

This paper introduces Standard Basis LoRA (SBoRA), a novel parameter-efficient fine-tuning approach for Large Language Models that builds upon the pioneering works of Low-Rank Adaptation (LoRA) and Orthogonal Adaptation.
Li, Kun, Wu, Haoxuan, Liu, Yuyang, Zhang, Tianqi, Wang, Zhuohan, Jiang, Zeyu, Po, Lai-Man, Yu, Wing-Yin   +7 more
core   +1 more source

Work Productivity Loss and Activity Impairment in Parents of Children With Juvenile Idiopathic Arthritis

ACR Open Rheumatology, Volume 8, Issue 10, October 2026.
Objective To determine the impact of juvenile idiopathic arthritis (JIA) on work productivity loss and daily activities of parents. Methods The multicenter Canada‐Netherlands Understanding Childhood Arthritis Network (UCAN) CAN‐DU and CURE study captures consecutive clinical and patient‐reported data for patients and parents since 2019.
Deborah A. Marshall, Rodrigo Dal Ben, Gillian R. Currie, Rae S. M. Yeung, Sebastiaan J. Vastert, Nico Wulffraat, Joost F. Swart, Susanne Benseler, on behalf of the UCAN CAN‐DU and UCAN CURE Consortia, Rae Yeung, Shirley Tse, Deborah Levy, Ronald Laxer, Brian Feldman, Elizaveta Limenis, Ruud Verstegen, Lynn Spiegel, Rayfel Schneider, Evelyn Rozenblyum, Jennifer Ji Young Lee, Alisa Rachlis, Susanne Benseler, Nicole Johnson, Muhammed Dhalla, Paivi Miettunen, Heinrike Schmeling, Marinka Twilt, Rebeka Stevenson, Deborah Marshall, Andrea Human, David Cabral, Jaime Guzman, Kim Morishita, Kristin Houghton, Lori Tucker, Tommy Gerschman, Herman Tam, Mercedes Chan, Ross Petty, Roman Jurencak, Nadia Luca, Ciarán Duffy, Tala El Tal, Roberta Berard, Jonathan Park, Erkan Demirkaya, Lily Lim, Adam Huber, Bianca Lang, Elizabeth Stringer, Chelsea DeCoste, Suzanne Ramsey, Dax G. Rumsey, Daniah Basodan, Lillian Lim, Hon Yan Ng, Jeanine McColl, Tara McGrath, Michelle Batthish, Tania Cellucci, Liane Heale, Claire LeBlanc, Gaëlle Chédeville, Rosie Scuccimarri, Sarah Campillo, Piya Lahiry, Paul Dancey, Nickolas Blanchette, Alan Rosenberg, Mehul Jariwala, Tristan Kerr, Kate Neufeld, Clare Hutchinson, Gordon Soon, Dieneke Schonenberg, Mariken Gruppen, Merlijn van den Berg, Giske Biesbroek, Philomine van Pelt, Marleen Verkaaik, Sylvia Kamphuis, Danielle Brinkman, Petra Hissink Muller, Ellen Schatorje, Esther Hoppenreijs, Annet van Royen‐Kerkhof, Sebastiaan Vastert, Berent Prakken, Erika Van Nieuwenhove, Joost Swart, Marc Jansen, Nico Wulffraat, Elizabeth Legger, Wineke Armbrust, Joseph Cafazzo, Maarten IJzerman, Alexander Mosoiu, Amy Xu, Arthur Cheng, Bruno Pereira, Trang Duong, Harper Cheng, Brenleigh Jebb, Gillian R. Currie, Rodrigo Dal Ben, Ravneet Sran, Elodie Boudes, Michelle Kip, Sytze de Rook, Regina de Geus   +109 more
wiley   +1 more source

Transformer‐Based Contextual Modeling for Predicting Calories From Recipes

Applied AI Letters, Volume 7, Issue 3, October 2026.
A transformer‐based regression model with token‐level attention pooling is proposed for predicting calorie content directly from unstructured recipe text. By fine‐tuning RoBERTa in an end‐to‐end manner, attention is learned to be focused on calorie‐relevant tokens such as ingredients, fats, and cooking methods.
Md. Siam Ansary, Amina Brinto
wiley   +1 more source

Sentiment Analysis of Imbalanced Dataset Through Data Augmentation and Generative Annotation Using DistilBERT and Low‐Rank Fine‐Tuning

Applied AI Letters, Volume 7, Issue 3, October 2026.
The proposed model takes an imbalanced English dataset as input and balances it by Generating Synthetic Tweets (GST) using GPT‐based paraphrasing. These new tweets are then annotated with one of 10 categorical labels representing their primary meaning, using another large language model like GPT.
Hossein Nekouei, Mohammad Hossein Moattar   +1 more
wiley   +1 more source

Laplacian-LoRA: Delaying Oversmoothing in Deep GCNs via Spectral Low-Rank Adaptation

CoRR
Oversmoothing is a fundamental limitation of deep graph convolutional networks (GCNs), causing node representations to collapse as depth increases. While many prior approaches mitigate this effect through architectural modifications or residual mechanisms, the underlying spectral cause of oversmoothing is often left implicit. We propose Laplacian-LoRA,
openaire   +2 more sources

Recent Advances in Microstrip Patch Antenna Optimization: Methods, Design Targets, and Emerging Trends

Applied Research, Volume 5, Issue 5, October 2026.
This systematic review synthesizes recent advances in Microstrip patch antennas (MPAs) optimization research, highlighting key design targets, optimization methodologies, performance trade‐offs, and application trends. The results demonstrate that MPA optimization is an inherently multivariable problem, with trade‐offs among antenna size, impedance ...
Madihah Zakaria, Noor Hidayah Mohd Yunus, Rifqi Irzuan Abdul Jalal, Jahariah Sampe, Hafiz Basarudin, Mohd Azraie Mohd Azmi, Hafiz Muhammad Jamsheed Nazir   +6 more
wiley   +1 more source