Results 151 to 160 of about 226,203 (262)

Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices

IEEE Transactions on Mobile Computing
Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resource constraints and system heterogeneity.
Jun Liu, Yunming Liao, Hongli Xu, Yang Xu, Jianchun Liu, Chen Qian   +5 more
openaire   +2 more sources

Microporous Microgel Assemblies Facilitating the Recruitment and Osteogenic Differentiation of Progenitor Cells for Bone Regeneration

Advanced Functional Materials, EarlyView.
There is a significant need for biomaterials with well‐defined stability and bioactivity to support tissue regeneration. In this study, we developed a tunable microgel platform that enables the decoupling of stiffness from porosity, thereby promoting bone regeneration.
Silvia Pravato, Haishuo Guan, Bianca M. Carrara, Mira Jacobs, Matteo Monticelli, Lukas Moser, Thomas Moragues, Andrew J. deMello, Tomaso Zambelli, Martin Ehrbar   +9 more
wiley   +1 more source

Research on the optimization of seamless steel pipe cooling process based on large language models

AIP Advances
To address technical challenges such as non-uniform cooling and microstructural delamination during the cooling process of seamless steel pipes, this study proposes an intelligent process parameter optimization approach that integrates a large language ...
Qiang Wu, Xi Chen, Mingwen Luo, Ao Li, Qing Yuan, Daliang Yu, Qingwei Dai   +6 more
doaj   +1 more source

GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, DoRA, and HiRA, enable lightweight adaptation of large pre-trained models via low-rank updates. However, existing PEFT approaches apply static, input-agnostic updates to all tokens, disregarding the varying importance and difficulty of different inputs.
Ou, Jie, Jiang, Shuaihong, Du, Yingjun, Snoek, Cees G. M.   +3 more
openaire   +2 more sources

Fermi Surface Nesting and Anomalous Hall Effect in Magnetically Frustrated Mn2PdIn

Advanced Functional Materials, EarlyView.
Mn2PdIn, a frustrated inverse Heusler alloy, showing electronic‐structure driven anomalous Hall effect with Weyl crossings, Fermi‐surface nesting and near‐zero magnetization ideal for low‐magnetization spintronics. Abstract Noncollinear magnets with near‐zero net magnetization and nontrivial bulk electronic topology hold significant promise for ...
Afsar Ahmed, Arnab Bhattacharya, Prashant Singh, Ajay Kumar, Tukai Singha, Anis Biswas, Yaroslav Mudryk, I. Das   +7 more
wiley   +1 more source

A Bespoke Programmable Interpenetrating Elastomer Network Composite Laryngeal Stent for Expedited Paediatric Laryngotracheal Reconstruction

Advanced Functional Materials, EarlyView.
A programmable interpenetrating double‐network architecture, created via 3D‐TIPS printing and resin infusion, synergistically combines thermoplastic and thermosetting elastomers to balance structural rigidity and surface softness—crucial for paediatric laryngeal stents.
Elizabeth F. Maughan, Lei Wu, Dong Zhang, Linxiao Wu, Graca Ferreira Vaz Pinto Mendes, Wanqiao J. Tu, Heping Ma, Toby J. Proctor, Colin R. Butler, Thomas Kjærgaard, Mark W. Lowdell, Martin A. Birchall, Robert E. Hynds, Richard Hewitt, Wenhui Song   +14 more
wiley   +1 more source

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing

Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the majority votes over the base classifier.
Fu, Chengyan, Wang, Wenjie
openaire   +2 more sources

MOFs and COFs in Electronics: Bridging the Gap between Intrinsic Properties and Measured Performance

Advanced Functional Materials, EarlyView.
Metal‐organic frameworks (MOFs) and covalent organic frameworks (COFs) hold promise for advanced electronics. However, discrepancies in reported electrical conductivities highlight the importance of measurement methodologies. This review explores intrinsic charge transport mechanisms and extrinsic factors influencing performance, and critically ...
Jonas F. Pöhls, R. Thomas Weitz
wiley   +1 more source

Near‐Infrared Organic Photovoltaic Electrodes for Subretinal Neurostimulation

Advanced Functional Materials, EarlyView.
Organic photovoltaic electrodes based on the D18:Y6 blend enable precise and light‐controlled activation of retinal ganglion cells in a degenerating retina. NIR Light‐driven activation of retinal ganglion cells, tunable stimulation parameters, and biocompatibility with human retinal organoids highlight their potential for next‐generation prosthetics ...
Andrea Corna, Katarina Gugujonovic, Manuela Schiek, Alessandro Bellapianta, Paul Werginz, Amelie Ziller, Markus Clark Scharber, Ahmad Salti, Matthias Bolz, Mihai Irimia‐Vladu, Günther Zeck   +10 more
wiley   +1 more source

PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization

The recent emergence of Large Language Models (LLMs) has heralded a new era of human-AI interaction. These sophisticated models, exemplified by Chat-GPT and its successors, have exhibited remarkable capabilities in language understanding. However, as these LLMs have undergone exponential growth, a crucial dimension that remains understudied is the ...
Clarke, Christopher, Heng, Yuzhao, Tang, Lingjia, Mars, Jason   +3 more
openaire   +2 more sources