检索结果-南通市图书馆

Optimizing Fine-Tuning in Quantized Language Models:An In-Depth Analysis of Key Variables

Computers, Materials & Continua 2025年第1期82卷 307-325页

作者： Ao Shen Zhiquan Lai Dongsheng Li Xiaoyu Hu National Key laboratory of Parallel and Distributed computing National University of Defense TechnologyChangsha410073China Strategic Assessments and Consultation Institute Academy of Military ScienceBeijing100091China

Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning *** this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader ***-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational *** these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA *** these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains *** study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM *** investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do *** insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized ***,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller *** study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM

关键词： Large-scale Language Model Parameter-Efficient Fine-Tuning parameter quantization key variable trainable parameters experimental analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Hilbert expansion of the Boltzmann equation in the incompressible Euler level in a channel

引用

science China Mathematics 2025年第1期68卷 39-88页

作者： Feimin Huang Weiqiang Wang Yong Wang Feng Xiao Academy of Mathematics and Systems science Chinese Academy of Sciences School of Mathematical sciences University of Chinese Academy of Sciences Key laboratory of computing and Stochastic Mathematics (Ministry of Education) School of Mathematics and StatisticsHunan Normal University

The study of the hydrodynamic limit of the Boltzmann equation with physical boundary is a challenging problem due to the appearance of the viscous and Knudsen boundary *** this paper,the hydrodynamic limit from the Boltzmann equation with the specular reflection boundary condition to the incompressible Euler equations in a channel is *** on the multi-scaled Hilbert expansion,the equations with boundary conditions and compatibility conditions for interior solutions,and viscous and Knudsen boundary layers are derived under different scaling,***,some uniform estimates for the interior solutions,and viscous and Knudsen boundary layers are *** the help of the L2-L∞framework and the uniform estimates obtained above,the solutions to the Boltzmann equation are constructed by the truncated Hilbert expansion with multiscales,and hence the hydrodynamic limit in the incompressible Euler level is justified.

关键词： Boltzmann equation incompressible Euler equations hydrodynamic limit Hilbert expansion specular reflection boundary condition viscous boundary layer Knudsen boundary layer

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Transforming Education with Photogrammetry:Creating Realistic 3D Objects for Augmented Reality Applications

引用

Computer Modeling in Engineering & sciences 2025年第1期142卷 185-208页

作者： Kaviyaraj Ravichandran Uma Mohan Department of Computational Intelligence School of ComputingSRM Institute of Science and TechnologyKattankulathur603203India

Augmented reality(AR)is an emerging dynamic technology that effectively supports education across different *** increased use of mobile devices has an even greater *** the demand for AR applications in education continues to increase,educators actively seek innovative and immersive methods to engage students in ***,exploring these possibilities also entails identifying and overcoming existing barriers to optimal educational ***,this surge in demand has prompted the identification of specific barriers,one of which is three-dimensional(3D)*** 3D objects for augmented reality education applications can be challenging and time-consuming for the *** address this,we have developed a pipeline that creates realistic 3D objects from the two-dimensional(2D)*** for augmented and virtual reality can then utilize these created 3D *** evaluated the proposed pipeline based on the usability of the 3D object and performance ***,with 117 respondents,the co-creation team was surveyed with openended questions to evaluate the precision of the 3D object created by the proposed photogrammetry *** analyzed the survey data using descriptive-analytical methods and found that the proposed pipeline produces 3D models that are positively accurate when compared to real-world objects,with an average mean score above *** study adds new knowledge in creating 3D objects for augmented reality applications by using the photogrammetry technique;finally,it discusses potential problems and future research directions for 3D objects in the education sector.

关键词： Augmented reality education immersive learning 3D object creation photogrammetry and StructureFromMotion

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Prominent cycling reversibility and kinetics enabled by CaTiO3 protective layer on Zn metal for aqueous Zn-ion batteries

引用

Journal of Energy Chemistry 2025年第1期100卷 245-258页

作者： Gaeun Lee Yong Nam Ahn Seongjoon So Chanwoo Park Jong-Seong Bae Taehyun Park Il Tae Kim Jaehyun Hur School of Chemical Biological and Battery Engineering Gachon University Seongnam Busan Center Korea Basic Science Institute

Aqueous Zn-ion batteries （AZIBs） have received considerable attention owing to their various advantages such as safety,low cost,simple battery assembly conditions,and high ionic ***,they still suffer from serious problems,including uncontrollable dendrite growth,corrosion,hydrogen evolution reaction （HER） from water decomposition,electrode passivation,and unexpected *** creation of a uniform artificial nanocrystal layer on the Zn anode surface is a promising strategy for resolving these ***,we propose the use of a perovskite CaTiO3（CTO） protective layer on Zn（CTO@Zn） as a promising approach for improving the performance of *** CTO artificial layer provides an efficient pathway for Zn ion diffusion towards the Zn metal because of the high dielectric constant （εr=180） and ferroelectric characteristics that enable the alignment of dipole moments and redistribute the Zn2+ions in the CTO *** avoiding the direct contact of the Zn anode with the electrolyte solution,the uneven dendrite growth,corrosion,parasitic side reactions,and HER are mitigated,while CTO retains its mechanical and chemical robustness during ***,CTO@Zn demonstrates an improved lifespan in a symmetric cell configuration compared with bare ***@Zn shows steady overpotential （～68 m V） for 1500 h at 1 mA cm-2/0.5 mA h cm-2,excelling bare ***,when paired with the V2O5-C cathode,the CTO@Zn//V2O5-C full battery delivers 148.4 mA h g-1（based on the mass of the cathode） after 300 *** study provides new insights into Zn metal anodes and the development of high-performance AZIBs.

关键词： Perovskite

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Copper homeostasis and neurodegenerative diseases

引用

Neural Regeneration Research 2025年第11期20卷 3124-3143页

作者： Yuanyuan Wang Daidi Li Kaifei Xu Guoqing Wang Feng Zhang International Research laboratory of Ethnomedicine of Ministry of Education Key Laboratory of Basic Pharmacology of Ministry of EducationLaboratory Animal Center and Key Laboratory of Basic Pharmacology of Guizhou ProvinceZunyi Medical UniversityZunyiGuizhou ProvinceChina

Copper,one of the most prolific transition metals in the body,is required for normal brain physiological activity and allows various functions to work normally through its range of *** homeostasis is meticulously maintained through a complex network of copper-dependent proteins,including copper transporters(CTR1 and CTR2),the two copper ion transporters the Cu-transporting ATPase 1(ATP7A)and Cu-transporting beta(ATP7B),and the three copper chaperones ATOX1,CCS,and *** in copper homeostasis can lead to either the deficiency or accumulation of copper in brain *** evidence suggests that abnormal copper metabolism or copper binding to various proteins,including ceruloplasmin and metallothionein,is involved in the pathogenesis of neurodegenerative ***,the exact mechanisms underlying these processes are not *** is a potent oxidant that increases reactive oxygen species production and promotes oxidative *** reactive oxygen species levels may further compromise mitochondrial integrity and cause mitochondrial *** oxygen species serve as key signaling molecules in copper-induced neuroinflammation,with elevated levels activating several critical inflammatory ***,copper can bind aberrantly to several neuronal proteins,including alphasynuclein,tau,superoxide dismutase 1,and huntingtin,thereby inducing neurotoxicity and ultimately cell *** study focuses on the latest literature evaluating the role of copper in neurodegenerative diseases,with a particular focus on copper-containing metalloenzymes and copper-binding proteins in the regulation of copper homeostasis and their involvement in neurodegenerative disease *** synthesizing the current findings on the functions of copper in oxidative stress,neuroinflammation,mitochondrial dysfunction,and protein misfolding,we aim to elucidate the mechanisms by which copper contributes to a wide range of heredit

关键词： Alzheimer's disease amyotrophic lateral sclerosis disease copper homeostasis copper toxicity Huntington's disease Menkes'disease multiple sclerosis neurodegenerative disease Parkinson's disease Wilson's disease

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Distributed optimal consensus control for multiagent systems based on event-triggered and prioritized experience replay strategies

引用

science China(Information sciences) 2025年第1期68卷 306-321页

作者： Cuijuan ZHANG Lianghao JI Shasha YANG Xing GUO Huaqing LI Chongqing Key laboratory of Image Cognition Chongqing University of Posts and Telecommunications Key laboratory of Intelligent Perception and computing of Anhui Province Anqing Normal University College of Electronic and Information Engineering Southwest University

This study uses event-triggered(ET) and reinforcement learning methods to investigate the optimal consensus control problem for cooperative-competitive multiagent systems. It proposes a novel distributed ET control strategy, which relies on a prioritized experience replay(PER) policy. This strategy not only conserves communication resources but also ensures acceptable system performance. To implement the proposed method, actor-critic(AC) dual-structured neural networks(NNs) are used to approximate the value function and control policy. In the AC NNs, the weight estimates for the NNs are updated at the moment of event triggering, resulting in a nonperiodic weight adjustment pattern. This approach decreases the computational cost in comparison with the traditional ET mechanism. The PER-based ET mechanism makes full use of valid historical data and effectively establishes a balance between system performance and communication resource ***, it does not require the following two conditions in most existing studies:(1) requirement of the system dynamics model to be known, and(2) persistent excitation. In addition, Zeno behavior is excluded from this study. Finally, a simulation is conducted to confirm the validity of the suggested approach.

关键词： multiagent systems event-triggered mechanism prioritized experience replay dual-structured neural networks optimal consensus control

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approach for Automating App Review Classification:Advancing Usability Metrics Classification with an Aspect-Based Sentiment Analysis Framework

引用

Computers, Materials & Continua 2025年第1期82卷 949-976页

作者： Nahed Alsaleh Reem Alnanih Nahed Alowidi Department of Computer science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer science College of Computer Science and EngineeringUniversity of HailHail81451Saudi Arabia

App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior *** research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and *** propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification *** analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,*** contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews *** advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.

关键词： Requirements Engineering(RE) app review analysis usabilitymetrics hybrid deep learning BERT-BiLSTM-CNN

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

引用

science China(Information sciences) 2025年

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词：

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tangled but ordered human mitochondrial tRNA maturation

引用

science China Life sciences 2025年

作者： Shi-Ying Yao Xiao-Long Zhou Key laboratory of RNA Innovation Science and Engineering CAS Center for Excellence in Molecular Cell Science Shanghai Institute of Biochemistry and Cell Biology Chinese Academy of Sciences University of Chinese Academy of Sciences Key laboratory of Systems Health science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences

Mitochondria are cellular organelles that originate from an endosymbiotic bacterial ancestor and are primarily responsible for ATP generation via oxidative phosphorylation (OXPHOS). OXPHOS is conducted by five mitochondrial respiratory complexes in the inner mitochondrial membrane. Human mitochondria possess a distinct genome, a small, circular, doublestranded DNA (mtDNA) of 16,569 base pairs.

关键词：

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Economic effect of China's carbon neutrality target under shared socioeconomic pathways

引用

science China Earth sciences 2025年第1期68卷 142-157页

作者： Zemiao LIU Xianjin HUANG Xinxian QI School of Geography and Ocean science Nanjing University Key laboratory of Carbon Neutrality and Territory Optimization Ministry of Natural Resources Frontiers science Center for Critical Earth Material Cycling Nanjing University

Economic feasibility is crucial for achieving the carbon neutrality target. However, current integrated assessments often underestimate the economic impacts of mitigation policies due to the lack of consideration of their economic benefits. This study integrates a warming-labour productivity model with a typical integrated assessment model using shared socioeconomic pathways. It simulates China's economic development and carbon emission levels under both baseline and carbon-neutral policy scenarios, evaluating the economic costs and benefits of emission reduction policies aimed at achieving carbon neutrality. These findings reveal the following:(1) The economic costs of emission reduction policies are projected to peak between 2050 and 2060, ranging from 0.41% to 9.37% of total GDP in the baseline scenario, primarily due to increased energy prices and R&D investments. These costs are expected to decline rapidly after 2070.(2) China's carbon-neutral policies will mitigate global warming, with the economic benefits of mitigation projected to reach 5.65% to 17.24% of China's total GDP by 2100.(3) Lowcarbon scenarios SSP1 and SSP4 could significantly reduce initial economic costs and advance the onset of net economic gains to 2060. This integrated assessment confirms that China's carbon neutrality target offers substantial net economic benefits in the long term. To minimize initial economic costs, efforts should focus on enhancing consumption-side transitions, upgrading lowcarbon technologies, and adopting new energy sources.

关键词： Climate change China Carbon neutrality Economic effects Policy

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：