Results 131 to 140 of about 227,550 (285)

AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs

Proceedings of the AAAI Conference on Artificial Intelligence
Fine-tuning pre-trained models has recently yielded remarkable performance gains in graph neural networks (GNNs). In addition to pre-training techniques, inspired by the latest work in the natural language fields, more recent work has shifted towards applying effective fine-tuning approaches, such as parameter-efficient fine-tuning (PEFT).
Li, Shengrui, Han, Xueting, Bai, Jing
openaire   +2 more sources

Tuning the Electronic Structure and Spin State of Fe─N─C Catalysts Using an Axial Oxygen Ligand and Fe Clusters for High‐Efficiency Rechargeable Zinc–Air Batteries

Advanced Functional Materials, EarlyView.
A FeN4─O/Clu@NC‐0.1Ac catalyst containing atomically‐dispersed FeN4─O sites (medium‐spin Fe2+) and Fe clusters delivered a half‐wave potential of 0.89 V for ORR and an overpotential of 330 mV at 10 mA cm−2 for OER in 0.1 m KOH. When the catalyst was used in a rechargeable Zn–air battery, a power density of 284.5 mW cm−2 was achieved with excellent ...
Yongfang Zhou, Yu Mao, Mengyao Chang, Ziyun Wang, Wenke Xie, Cuizhu Ye, Shanghai Wei, Lars Thomsen, Geoffrey I. N. Waterhouse   +8 more
wiley   +1 more source

PRISM-Med: Parameter-Efficient Robust Interdomain Specialty Model for Medical Language Tasks

IEEE Access
Language Models (LMs) have shown remarkable potential in healthcare applications, yet their widespread adoption faces challenges in achieving consistent performance across diverse medical specialties while maintaining parameter efficiency.
Jieui Kang, Hyungon Ryu, Jaehyeong Sim
doaj   +1 more source

ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation

, 2018
We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time.
Ciccone, Marco, Lattari, Francesco, Masci, Jonathan, Matteucci, Matteo, Visin, Francesco   +4 more
core  

Formation of Stable Amorphous Calcium Phosphate and Collagen Assemblies by a Versatile Spray‐Drying Approach

Advanced Functional Materials, EarlyView.
Amorphous calcium phosphate (ACP) microparticles with long‐term and thermal stability are prepared with or without collagen using a scalable one‐pot spray‐drying process. Under simulated physiological conditions, they crystallize into biomimetic bone mineral and, when combined with collagen, form extrudable, fibrillar bone‐like 3D constructs.
Camila Bussola Tovani, Nessma Bennaceur, Celina Benkhellat, Tristan Georges, Clara Doisneau, Vaskar Sardhalia, Thierry Azaïs, Flora Lemaire, Halima Kerdjoudj, Mohamed Selmane, Capucine Sassoye, Marie Albéric, Cédric Boissière, Nadine Nassif   +13 more
wiley   +1 more source

A new low-rank adaptation method for brain structure and metastasis segmentation via decoupled principal weight direction and magnitude

Scientific Reports
Deep learning techniques have become pivotal in medical image segmentation, but their success often relies on large, manually annotated datasets, which are expensive and labor-intensive to obtain.
Hancan Zhu, Hongxia Yang, Yaqing Wang, Keli Hu, Guanghua He, Jia Zhou, Zhong Li, Alzheimer’s Disease Neuroimaging Initiative   +7 more
doaj   +1 more source

SumLLaMA: Efficient Contrastive Representations and Fine-Tuned Adapters for Bug Report Summarization

IEEE Access
In software maintenance, concise summaries of bug reports are crucial, significantly enhancing developer efficiency and ultimately improving software quality and user experience. Large language models (LLMs) have become the standard method for bug report
Bangmeng Xiang, Yunna Shao
doaj   +1 more source

Spectrally Tunable 2D Material‐Based Infrared Photodetectors for Intelligent Optoelectronics

Advanced Functional Materials, EarlyView.
Intelligent optoelectronics through spectral engineering of 2D material‐based infrared photodetectors. Abstract The evolution of intelligent optoelectronic systems is driven by artificial intelligence (AI). However, their practical realization hinges on the ability to dynamically capture and process optical signals across a broad infrared (IR) spectrum.
Junheon Ha, Yingshan Ma, Yong Nam An, Sung‐Un An, Hyeon Hak Jung, Suvi‐Tuuli Varjamo, Jiwon Yoo, Junho Min, Hanvit Kim, Faisal Ahmed, Sang Hoon Chae, Young Min Song, Weiwei Cai, Tawfique Hasan, Zhipei Sun, Dong‐Ho Kang, Hyeon‐Jin Shin, Yunyun Dai, Hoon Hahn Yoon   +18 more
wiley   +1 more source

Task-Agnostic Adaptive Activation Scaling Network for LLMs

IEEE Access
The advent of Large Language Models (LLMs) has revolutionized Natural Language Processing (NLP), offering unprecedented capabilities for understanding and generating human-like texts.
Ni Jia, Tong Liu, Jiadi Chen, Ying Zhang, Song Han   +4 more
doaj   +1 more source

Endothelial Cells Angiogenesis in Sulfated Glycosaminoglycan (GAG) Hydrogels Enhanced by Bioactive Glass‐Released Ions

Advanced Functional Materials, EarlyView.
A mechanically tunable hydrogel composed of gelatin, chondroitin sulfate and laminin promotes angiogenesis in vitro without the supplement of growth factors. Endothelial cells morphogenesis was further enhanced by medium conditioned with bioactive glass 58S‐released ions (Ca and Si), thus offering a promising strategy to vascularize 3D tissue ...
Marco Piazzoni, Ilaria Borghi, Francesca Cadamuro, Sophia Dalfino, Riccardo Campanile, Sofia Nizzolo, Valeria Cassina, Francesca Tallia, Julian R. Jones, Francesco Mantegazza, Sabrina Bertini, Lorenzo Moroni, Francesco Nicotra, Laura Russo   +13 more
wiley   +1 more source