Results 31 to 40 of about 9,649,421 (248)

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

CoRR
ICML ...
Tao Li, Zhengbao He, Yujun Li, Yasheng Wang, Lifeng Shang, Xiaolin Huang   +5 more
openaire   +4 more sources

Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions

Advanced Science, EarlyView.
A unified time‐series forecasting framework learns transferable battery capacity‐degradation patterns from 20 heterogeneous datasets spanning chemistries, formats, temperatures, and cycling conditions. A single model delivers competitive predictions on both known and previously unseen datasets, while physics‐guided representation learning improves ...
Joey Chan, Huan Wang, Zhen Chen, Haoyu Pan, Wei Wu, Zirong Wang, Ershun Pan, Min Xie, Lifeng Xi   +8 more
wiley   +1 more source

Activation-Guided Layer Selection for LoRA

Information
Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for large language models (LLMs). LoRA’s benefits stem from its light weight and modular adapters. Standard LoRA applies adapters uniformly across all
Aditya Dawadikar, Pooja Shyamsundar, Rashmi Vishwanath Bhat, Navrati Saxena   +3 more
doaj   +1 more source

Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications

Advanced Energy Materials, EarlyView.
Machine learning interatomic potentials bridge quantum accuracy and computational efficiency for materials discovery. Architectures from Gaussian process regression to equivariant graph neural networks, training strategies including active learning and foundation models, and applications in solid‐state electrolytes, batteries, electrocatalysts ...
In Kee Park, Saeed Pourasad, Jinhong Mun, Arunkumar Chitteth Rajan, Tae Hyeon Park, Anand Rohit, Mohammad Zafari, Tan‐Lien Pham, Eunjae Jung, Bonseung Koo, Miran Ha, Gi Beom Sim, Hyun Gyu Park, Won Woong Choi, Kwanghyeon Jo, Soohaeng Yoo Willow, David ChangMo Yang, Chang Woo Myung, Geunsik Lee, Kwang S. Kim   +19 more
wiley   +1 more source

GroupLoRA: Enhancing Rank Effectiveness Through Group-Wise Decomposition for Low-Rank Adaptation

IEEE Access
The rapid advancement of Large Language Models (LLMs) and Large Vision Models (LVMs) has achieved breakthrough performance but has also created significant deployment challenges due to their massive scale, often exceeding 100 billion parameters ...
Jaesung Jun, Youngmin Ro
doaj   +1 more source

Complement Activation Linked to Type II Interferon Signaling in Still Disease

Arthritis &Rheumatology, EarlyView.
Objective Still disease (SD) is an autoinflammatory syndrome characterized by innate immune dysregulation. Although complement can drive inflammation, its involvement in SD remains to be defined. Thus, we aimed to assess complement activation in SD. Methods Complement was assessed using transcriptomic, proteomic, and in vitro approaches. RNA sequencing
Freya M. C. H. Huijsmans, Tabea Thalheim, Alejandra Bodelón, Greta Rogani, Lyanne J. P. M. Sijbers, Remco G. A. Erkens, Aafke de Ligt, Rianne Scholman, Aron Brinker, Gisella B. Beretta, Nienke M. Ter Haar, Thomas Vogl, Johannes Roth, Trang T. Duong, Sytze de Roock, Joost F. Swart, Deborah A. Marshall, Susanne M. Benseler, Rae S. M. Yeung, Christoph Kessel, Sebastiaan J. Vastert, Emely L. Verweyen, Jorg van Loosdregt, on behalf of the UCAN CAN‐DU/UCAN CURE Consortia and the One Child Every Child Initiative, Adam Huber, Bianca Lang, Chelsea DeCoste, Elizabeth Stringer, Suzanne Ramsey, Alan Rosenberg, Kate Neufeld, Mehul Jariwala, Tristan Kerr, Alexander Mosoiu, Alisa Rachlis, Amy Xu, Arthur Cheng, Brenleigh Jebb, Brian Feldman, Bruno Pereira, Deborah Levy, Dilan Dissanayake, Elizaveta Limenis, Evelyn Rozenblyum, Harper Cheng, Jennifer Ji Young Lee, Lynn Spiegel, Rayfel Schneider, Ronald Laxer, Ruud Verstegen, Shirley Tse, Andrea Human, David Cabral, Herman Tam, Jaime Guzman, Kim Morishita, Kristin Houghton, Lori Tucker, Mercedes Chan, Ross Petty, Tommy Gerschman, Annet van Royen‐Kerkhof, Berent Prakken, Erika Van Nieuwenhove, Marc Jansen, Nico Wulffraat, Ciarán Duffy, Nadia Luca, Roman Jurencak, Tala El Tal, Claire LeBlanc, Gaëlle Chédeville, Piya Lahiry, Rosie Scuccimarri, Sarah Campillo, Clare Hutchinson, Daniah Basodan, Dax G Rumsey, Hon Yan Ng, Jeanine McColl, Lillian Lim, Tara McGrath, Danielle Brinkman, Petra Hissink Muller, Elizabeth Legger, Wineke Armbrust, Ellen Schatorje, Esther Hoppenreijs, Elodie Boudes, Gillian Currie, Heinrike Schmeling, Muhammed Dhalla, Nicole Johnson, Paivi Miettunen, Ravneet Sran, Rebeka Stevenson, Erkan Demirkaya, Jonathan Park, Roberta Berard, Giske Biesbroek, Mariken Gruppen, Gordon Soon, Joseph Cafazzo, Liane Heale, Michelle Batthish, Tania Cellucci, Lily Lim, Maarten IJzerman, Marinka Twilt, Marleen Verkaaik, Philomine van Pelt, Sylvia Kamphuis, Michelle Kip, Nicholas Blanchette, Paul Dancey, Regina de Geus   +115 more
wiley   +1 more source

Describing Land Cover Changes via Multi-Temporal Remote Sensing Image Captioning Using LLM, ViT, and LoRA

Remote Sensing
Describing land cover changes from multi-temporal remote sensing imagery requires capturing both visual transformations and their semantic meaning in natural language. Existing methods often struggle to balance visual accuracy with descriptive coherence.
Javier Lamar León, Vitor Nogueira, Pedro Salgueiro, Paulo Quaresma   +3 more
doaj   +1 more source

Open-Vocabulary Speech Emotion Recognition Based on Improved Low-Rank Adaptation [PDF]

Jisuanji kexue yu tansuo
The emergence of audio large language models (AudioLLMs) has propelled speech emotion recognition (SER) from simple categorical discrimination toward profound emotional understanding, aiming to transcend current closed-set classification paradigms by ...
LIU Kangwei, DING Hanyu, GAO Lijian, MAO Qirong
doaj   +1 more source

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

CoRR
Camera-Ready Version for ICLR 2025; technical corrections to previous ...
Zhengbo Wang, Jian Liang 0001, Ran He 0001, Zilei Wang, Tieniu Tan   +4 more
openaire   +4 more sources

Recent Non‐Suicidal Self‐Injury in Autistic Adolescents and Adults: Characteristics, Clinical Correlates and Suicidal Thoughts and Behaviors

Autism Research, EarlyView.
ABSTRACT Non‐suicidal self‐injury (NSSI) is prevalent among autistic adolescents and adults, yet research on its clinical characteristics, functions, and association with suicidal thoughts and behaviors (STBs) in this population remains limited. This study compared these domains between autistic adolescents and adults with and without recent NSSI.
Safaa Eldeeb, Ligia Antezana, Caitlin M. Conner, Kelly B. Beck, Sarah E. Victor, Aliona Tsypes, Lori N. Scott, Carla A. Mazefsky   +7 more
wiley   +1 more source