Results 91 to 100 of about 124,133 (290)

Soft Mechanical‐Electrical Logic Using Liquid Metal‐Filled 3D‐Printed Architectures

Advanced Engineering Materials, EarlyView.
We present 3D‐printed soft mechanical–electrical logic elements that use liquid metal–filled silicone tubes actuated by thermoplastic polyurethane/polylactic acid (TPU/PLA) architectures to produce Boolean operations. Complementary normally open and normally closed unit cells perform repeatable binary transitions and can be combined into more complex ...
Christoph Lehmann, Ryan Kalgreen, Laura M. Comella   +2 more
wiley   +1 more source

Integrating Fine-Tuning and Retrieval-Augmented Generation for Healthcare AI Systems: A Scoping Review

Bioengineering
(1) Background: Large language models (LLMs) show promise in healthcare but are constrained by hallucinations, static knowledge, and limited domain specificity. Fine-tuning (FT) and retrieval-augmented generation (RAG) offer complementary solutions, with
Bernardo G. Collaco, Prabha Srinivasagam, Cesar A. Gomez-Cabello, Syed Ali Haider, Ariana Genovese, Nadia G. Wood, Sanjay Bagaria, Mark A. Lifson, Antonio Jorge Forte   +8 more
doaj   +1 more source

Direct Metal Deposition of Graphene–Ti28Nb35.4Zr Matrix Composites With Enhanced Mechanical, Corrosion, and Biocompatibility Properties for Bone Implants

Advanced Engineering Materials, EarlyView.
Graphene nanoplatelet (0.1 wt.%) reinforcement significantly enhances the performance of β Ti‐28Nb‐35.4Zr alloy. Grain refinement, reduced water contact angle, and improved surface characteristics promote osteoblast adhesion and complete surface coverage after 7 days.
Khurram Munir, Jixing Lin, Yuncang Li, Li Zhu, Paul F. A. Wright, Cuie Wen   +5 more
wiley   +1 more source

SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning

Findings of the Association for Computational Linguistics ACL 2024
Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for adjustments to only a minor fraction of the parameters of these LLMs.
Zhihao Wen, Jie Zhang, Yuan Fang 0001
openaire   +3 more sources

Enhancing Bubble Removal in Geometry‐Optimized Electrodes

Advanced Engineering Materials, EarlyView.
3D‐printed lattice electrodes outperform stochastic foams in alkaline water electrolysis despite 20%–25% lower surface area. Straight flow channels generate Venturi‐like bubble entrainment, suppressing gas accumulation that renders foam interiors electrochemically inactive.
Florian Wiesner, Peter Förster, Alexander Limper, Anselm Brodersen, Matthias Wessling, John Linkhorst   +5 more
wiley   +1 more source

A Hardware-Aware Efficient LLM for Multimedia Understanding via Dynamic Rank Adaptation and Structured Pruning

IEEE Access
Large Language Models (LLMs) have been applied in multiple fields due to their language understanding, multi-modal interaction, and logical reasoning capabilities.
Ruxing Yang, Luyao Liang
doaj   +1 more source

GateRA: Token-aware Modulation for Parameter-Efficient Fine-tuning

Proceedings of the AAAI Conference on Artificial Intelligence
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   +3 more
openaire   +3 more sources

Microstructure Reconstruction in Battery Electrodes Using Machine Learning Based on Low‐Voltage Focused Ion Beam–Scanning Electron Microscopy Tomography Images

Advanced Engineering Materials, EarlyView.
Low‐voltage FIB‐SEM tomography combined with a image preprocessing pipeline improves phase contrast and enables reliable machine‐learning segmentation of conductive networks in lithium‐ion battery electrodes. Structural descriptors are extracted from segmented images, done semimanually and automated, and compared.
Lisa Beran, Vincent Nebel, Dominik Perius, Kshitij Kumar, Yannis Heim, Laura Bies, Tobias Kraus   +6 more
wiley   +1 more source

Parameter-Efficient Fine-Tuning via Meta-Regularizer

International Journal of Computer Vision
Abstract Pre-trained vision-language models ( e.g ., CLIP) have shown impressive success in various computer vision tasks with their generalization capability. Recently, parameter-efficient fine-tuning (PEFT) approaches have been actively explored to effectively and ...
Jinyoung Park 0005, Juyeon Ko, Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim   +4 more
openaire   +1 more source

Influence of Geometric Design on Mechanical Performance of Auxetic Metastructure

Advanced Engineering Materials, EarlyView.
Strategic geometric reinforcement transforms auxetic performance. This study evaluates 3D‐printed arrowhead metastructures, revealing that a modified design with local ring reinforcement suppresses premature failure to achieve superior energy absorption and structural efficiency.
Muhammad Gulzari, Supharoek Sornsomrit, Muhammad Ayaz Akbar, Stephan Rudykh   +3 more
wiley   +1 more source