Results 101 to 110 of about 33,388 (259)

NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency.
Zhang, Zhi, Shen, Yixian, Cao, Congfeng, Shutova, Ekaterina   +3 more
openaire   +2 more sources

Prospects of Electric Field Control in Perpendicular Magnetic Tunnel Junctions and Emerging 2D Spintronics for Ultralow Energy Memory and Logic Devices

Advanced Functional Materials, EarlyView.
Electric control of magnetic tunnel junctions offers a path to drastically reduce the energy requirements of the device. Electric field control of magnetization can be realized in a multitude of ways. These mechanisms can be integrated into existing spintronic devices to further reduce the operational energy.
Will Echtenkamp, Brahmdutta Dixit, Yifei Yang, Deyuan Lyu, Thomas Peterson, Qi Jia, Yu‐Chia Chen, Jian‐Ping Wang   +7 more
wiley   +1 more source

DualDyConvNet: Dual-Stream Dynamic Convolution Network via Parameter-Efficient Fine-Tuning for Predicting Motor Prognosis in Subacute Stroke

IEEE Transactions on Neural Systems and Rehabilitation Engineering
Stroke is a significant impediment on a global scale, with the prognosis for motor ability contingent on initial rehabilitation and the severity of the injury.
Yunjeong Jang, Joohye Jeong, Yun Kwan Kim, Da-Hye Kim, Wanjoo Park, Laehyun Kim, Yun-Hee Kim, Minji Lee   +7 more
doaj   +1 more source

Bimetallic Nanoparticles as Cocatalysts for Photocatalytic Hydrogen Production

Advanced Functional Materials, EarlyView.
Recent developments have introduced bimetallic nanoparticles as effective cocatalysts for photocatalytic systems. This review explores the rapidly expanding research on bimetallic cocatalysts for photocatalytic production of hydrogen, emphasizing the creation of carrier‐selective contacts, localized surface plasmon resonance effects, methodologies for ...
Yufen Chen, Asier Agrelo‐Lestón, Ignasi Burgués‐Ceballos, Jordi Llorca, Lluís Soler   +4 more
wiley   +1 more source

Automatic Scoring of Arabic Essays: A Parameter-Efficient Approach for Grammatical Assessment

IEEE Access
Automatic essay scoring (AES) utilizes computational methods to evaluate written essays, offering an efficient approach to grading in various educational contexts. Essays can have multiple scoring criteria.
Somaia Mahmoud, Emad Nabil, Marwan Torki
doaj   +1 more source

Hydra: Multi-head low-rank adaptation for parameter efficient fine-tuning

Neural Networks
The recent surge in large-scale foundation models has spurred the development of efficient methods for adapting these models to various downstream tasks. Low-rank adaptation methods, such as LoRA, have gained significant attention due to their outstanding parameter efficiency and no additional inference latency.
Sanghyeon Kim, Hyunmo Yang, Yunghyun Kim, Youngjoon Hong, Eunbyung Park   +4 more
openaire   +3 more sources

Low‐Symmetry Weyl Semimetals: A Path to Ideal Topological States

Advanced Functional Materials, EarlyView.
This study presents a theoretical framework for realizing ideal Weyl semimetals, where Weyl nodes are well‐isolated at the Fermi level. The approach is exemplified in the low‐symmetry material Cu2SnSe3, which exhibits tunable topological phases, current‐induced orbital magnetization, and a strong circular photogalvanic effect, making it a promising ...
Darius‐Alexandru Deaconu, Varun Shah, Rodion Vladimirovich Belosludov, Mohammad Saeed Bahramy   +3 more
wiley   +1 more source

DC-LoRA: Domain correlation low-rank adaptation for domain incremental learning

High-Confidence Computing
Continual learning, characterized by the sequential acquisition of multiple tasks, has emerged as a prominent challenge in deep learning. During the process of continual learning, deep neural networks experience a phenomenon known as catastrophic ...
Lin Li, Shiye Wang, Changsheng Li, Ye Yuan, Guoren Wang   +4 more
doaj   +1 more source

Modulating Two‐Photon Absorption in a Pyrene‐Based MOF Series: An In‐Depth Investigation of Structure–Property Relationships

Advanced Functional Materials, EarlyView.
This study investigates H4TBAPy‐based metal–organic frameworks (MOFs) ‐ NU‐1000, NU‐901, SrTBAPy, and BaTBAPy ‐ for multiphoton absorption (MPA) performance. It observes topology‐dependent variations in the 2PA cross‐section, with BaTBAPy exhibiting the highest activity.
Simon N. Deger, Helmy Pacheco Hernandez, Yang Cui, Hongxing Hao, Vanessa Ramm, David C. Mayer, Khai‐Nghi Truong, Roland A. Fischer, Jürgen Hauer, Mariana Kozlowska, Alexander Pöthig   +10 more
wiley   +1 more source

Fine-Tuning the Qwen2.5-VL Model for Intelligent Applications in the Electrical Domain

EAI Endorsed Transactions on Energy Web
This study explores the fine-tuning application of the Qwen2.5-VL multi modal large model in the electrical domain. The electrical industry faces numerous challenges in maintaining and managing complex electrical systems.
Yao Song, Chunli Lv, Kun Zhu, Xiaobin Qiu   +3 more
doaj   +1 more source