检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xi, Zekun Yin, Wenbiao Fang, Jizhan Wu, Jialong Fang, Runnan Zhang, Ningyu Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Tongyi Lab Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model’s predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, novelty, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, unoriginal, and repetitive outputs. To address these issues, we propose OmniThink, a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they slowly deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Functional Testing and Repair for ReRAM-Based Deep-Learning Accelerators

IEEE Design and Test

引用

IEEE Design and Test 2025年第3期42卷 66-73页

作者： Li, Wen Wang, Ying Li, Huawei Li, Xiaowei Zou, Kaiwei Shanxi University School of Computer and Information Technology Shanxi Taiyuan030006 China Institute of Big Data Science and Industry Shanxi University Shanxi Taiyuan030006 China State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Tsinghua University Department of Electronic Engineering Beijing100084 China

Editor’s notes: This article offers an overview of the RRAMedy framework, designed to perform online testing, fault diagnosis, and fault mitigation in resistive random-access memory (ReRAM) devices, specifically in the context of ReRAM crossbar-based implementations for AI hardware acceleration. —Jyotika Athavale, Synopsys, USA —Haralampos-G. Stratigopoulos, Sorbonne Université, CNRS, LIP6, France. © 2013 IEEE.

关键词： Accuracy Fault tolerant systems Fault tolerance Deep learning Image edge detection Fault detection Computational modeling Training Reliability Hafnium

来源：评论

学校读者我要写书评

暂无评论

MSMAE-Net: multi-semantic and multi-attention enhanced network for image forgery localization

引用

Signal, Image and Video Processing 2025年第7期19卷 1-11页

作者： Liao, Jianjun Su, Lichao Lu, Menghan Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

The popularization of modern digital image technology has brought convenience to us, but it also poses many risks. The advancement of image editing software allows anyone to modify image content effortlessly. If these modified images are abused, they can severely impact societal safety and stability. To address these risks, we propose an end-to-end multi-scale collaborative enhancement image forgery localization network, termed MSMAE-Net. The method first employs a multi-branch feature extractor to initially capture both global and local information, with each branch optimized for different contextual information and features of the image. Next, to enhance the model’s ability to capture forged traces at various levels while maintaining the correlation between different spatial hierarchies, a boundary information aggregation module is designed. By constructing multiple branches with different receptive fields and collaborative learning with each other, a nested collaborative enhancement branch is designed to make the backbone network pay more attention to key features, so as to obtain better feature representation capability. Furthermore, to further fuse different semantic information, a novel strongly compatible semantic attention fusion module is proposed in this paper. Finally, an attention enhancement module is introduced in the localization of forgery regions to adaptively concentrate on key forged areas in the image and effectively capture the relationships between different pixels. In the experiments, we demonstrate that MSMAE-Net exhibits significant advantages in both localization accuracy and robustness in complex forgery scenarios when compared to other SOTA image forgery detection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSDK-LegalSum: improving legal judgment summarization using logical structure and domain knowledge

引用

Journal of King Saud University - Computer and Information Sciences 2025年第1期37卷 1-15页

作者： Gao, Wei Yu, Shuai Qin, Yongbin Yang, Caiwei Huang, Ruizhang Chen, Yanping Lin, Chuan Engineering Research Center of Text Computing & CognitiveIntelligence Ministry of Education Guizhou University Guizhou Huaxi Guiyang 550025 China State Key Laboratory of Public Big Data Guizhou University Guizhou Huaxi Guiyang 550025 China College of Computer Science and Technology Guizhou University Guizhou Huaxi Guiyang 550025 China

Legal judgment summarization enhances the efficiency and accuracy of processing and retrieving similar cases by distilling key information from legal judgment documents. Legal judgments, which record the trial process and outcome, tend to have lengthy texts. However, most existing methods for legal judgment summarization struggle to effectively handle long texts and focus only on the serialized text information, neglecting the auxiliary role of the document’s logical structure in generating summaries. Additionally, legal judgment documents contain extensive domain knowledge formed by professional legal terminology, which is crucial for accurately understanding and analyzing the content of the documents. We propose a method to improve the quality of legal judgment summaries by utilizing logical structures and domain knowledge (LSDK-LegalSum). Specifically, we first use a multi-label document classification approach to divide the legal judgment into four parts: ‘Type’, ‘Claim’, ‘Fact’ and ‘Result’, then generate a summary of the ‘Type’ part, and combine it with the ‘Claim’ part to create a new summary, and so forth until the final summary is produced. Moreover, the case descriptions in legal judgments cause substantial textual noise;therefore, we employ a text-denoising method that integrates domain knowledge to further enhance the performance of the summaries. Extensive experiments on the CAIL2020 legal summarization dataset have shown that our method achieves improvements of 8.37, 16.64, and 13.07 percentage points in Rouge-1, Rouge-2, and Rouge-L scores respectively over the state-of-the-art models. This demonstrates that our method not only produces concise and semantically complete summaries but also ensures that the content is logically rigorous and well-organized, meeting practical needs more effectively. © The Author(s) 2025.

关键词： Abstractive summarization Domain knowledge Legal judgment summarization Logical structure Low-source summarization

来源：评论

学校读者我要写书评

暂无评论

NSPG-Miner: Mining Repetitive Negative Sequential Patterns

arXiv

引用

arXiv 2025年

作者： Li, Yan Wang, Zhulin Liu, Jing Guo, Lei Fournier-Viger, Philippe Wu, Youxi Wu, Xindong School of Economics and Management Hebei University of Technology Tianjin300401 China School of Artificial Intelligence Hebei University of Technology Tianjin300401 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin300401 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China Hebei Key Laboratory of Big Data Computing 300401 China Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology Hefei230009 China

Sequential pattern mining (SPM) with gap constraints (or repetitive SPM or tandem repeat discovery in bioinformatics) can find frequent repetitive subsequences satisfying gap constraints, which are called positive sequential patterns with gap constraints (PSPGs). However, classical SPM with gap constraints cannot find the frequent missing items in the PSPGs. To tackle this issue, this paper explores negative sequential patterns with gap constraints (NSPGs). We propose an efficient NSPG-Miner algorithm that can mine both frequent PSPGs and NSPGs simultaneously. To effectively reduce candidate patterns, we propose a pattern join strategy with negative patterns which can generate both positive and negative candidate patterns at the same time. To calculate the support (frequency of occurrence) of a pattern in each sequence, we explore a NegPair algorithm that employs a key-value pair array structure to deal with the gap constraints and the negative items simultaneously and can avoid redundant rescanning of the original sequence, thus improving the efficiency of the algorithm. To report the performance of NSPG-Miner, 11 competitive algorithms and 11 datasets are employed. The experimental results not only validate the effectiveness of the strategies adopted by NSPG-Miner, but also verify that NSPG-Miner can discover more valuable information than the state-ofthe-art algorithms. Algorithms and datasets can be downloaded from https://***/wuc567/PatternMining/tree/master/NSPG-Miner. Copyright © 2025, The Authors. All rights reserved.

关键词： Miners

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Graph Contrastive Learning for Wind Power Forecasting

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Liu, Guiyan Zhang, Yajuan Zhang, Ping Gu, Junhua Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Hebei University of Technology Hebei Province Key Laboratory of Big Data Calculation School of Artificial Intelligence Tianjin300401 China Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Artificial Intelligence Tianjin300401 China

Accurate and robust wind power forecasting plays a crucial role in ensuring the safety and stability of the power system. Hybrid spatiotemporal forecasting models based on graph convolutional networks have received widespread attention due to their advantages in spatial feature extraction. However, these methods are susceptible to the quality of the generated graph due to data noise and missing issues, resulting in suboptimal performance. In this paper, we propose a hybrid deep learning model based on spatiotemporal graph contrastive learning to address the above issues. Specifically, the model's encoder combines an adaptive graph convolutional network with LSTM to capture fine-grained spatiotemporal dependencies. To enhance the robustness of the encoder against data noise, we apply feature-level and topology-level data augmentation techniques to the model's input and design two contrastive learning auxiliary tasks from the temporal and spatial dimensions, respectively. Furthermore, to capture more comprehensive spatial correlations, we construct an adaptive graph by fusing the static graph with a learnable parameter matrix. Extensive experimental results on two realworld datasets demonstrate that our proposed model significantly outperforms other state-of-the-art methods. Code is available at https://***/lgyjayou/SGCLWPF. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: accelerating distributed GNN training leveraging feature-centric model migration 25

LeapGNN: accelerating distributed GNN training leveraging fe...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Xuechen Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University and Zhejiang Lab and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Interference-Aware Routing,Wavelength and Power Allocation in C+L+S Multi-Band Optical Networks

引用

China Communications 2025年第4期22卷 129-142页

作者： Zhang Xu Xie Wang Feng Chuan Zeng Hankun Zhou Shanshan Zhang Fan Gong Xiaoxue School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China

Multi-band optical networks are a potential technology for increasing network ***,the strong interference and non-uniformity between wavelengths in multi-band optical networks have become a bottleneck restricting the transmission capacity of multi-band optical *** overcome these challenges,it is particularly important to implement optical power optimization targeting wavelength ***,based on the generalized Gaussian noise model,we first formulate an optimization model for the problems of routing,modulation format,wavelength,and power allocation in C+L+S multi-band optical *** objective function is to maximize the average link capacity of the network while ensuring that the Optical Signal-to-Noise(OSNR)threshold of the service request is not ***,we propose a NonLinear Interferenceaware(NLI-aware)routing,modulation format,wavelength,and power allocation ***,we conduct simulations under different test *** simulation results indicate that our algorithm can effectively reduce the blocking probability by 23.5%and improve the average link capacity by 3.78%in C+L+S multi-band optical networks.

关键词： multiband optical communications multiband optical networks power allocation wavelength assignment

来源：评论

学校读者我要写书评

暂无评论

AutoMiner: Reinforcement Learning-Based Mining Attack Simulator 24th

AutoMiner: Reinforcement Learning-Based Mining Attack Simula...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Li, Wei Xue, Lide Han, Ziyang Chen, Bingren Zhang, Xishan Zhou, Xuehai University of Science and Technology of China Hefei China ShangHai Municipal Big Data Center Shanghai China Anban Tech Co. Shanghai China State Key Laboratory of Processor Technologies Institute of Computing Technology Chinese Academy of Sciences Beijing China Cambricon Technologies Beijing China

ISBN: (纸本)9789819615247

As blockchain technology rapidly advances, it faces significant security threats from attacks like selfish mining, which exploit consensus algorithm vulnerabilities, undermining system security. Traditional analysis methods, primarily reliant on Markov models, are often utilized to address these complex threats. However, these methods frequently fall short in accurately simulating the multifaceted nature of blockchain attacks, leading to gaps in security measures. To bridge this gap, we introduce AutoMiner, an innovative reinforcement learning-based framework that integrates Miner Monte Carlo Tree Search (MMCTS) with Long Short-Term Memory (LSTM) networks for simulating and detecting potential mining attacks within the Proof of Work (PoW) framework. Our experimental results demonstrate AutoMiner’s capability to outperform traditional selfish and honest mining strategies, achieving up to 20% higher profits under specific scenarios. This highlights AutoMiner’s potential in enhancing blockchain security by providing a more comprehensive and effective approach to analyzing and mitigating mining attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain Reinforcement learning Security analysis

来源：评论

学校读者我要写书评

暂无评论

Archive-based multiple feature construction method using adaptive genetic programming

引用

Memetic computing 2025年第2期17卷 1-16页

作者： Jia, Kaixuan Zhang, Fan Gao, Xiaoying Ma, Jianbin College of Information Science and Technology Hebei Agricultural University Baoding China College of Information Science and Technology Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural University Baoding China School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

The quality of features is an important factor that affects the classification performance of machine learning algorithms. Feature construction based on Genetic Programming (GP) can automatically create more discriminative features, sometimes greatly improving classification performance. However, constructing a single feature or a small number of features may make the linkage information between labels and features insufficient, resulting in poor classification performance, so we introduce a multi-feature construction method. In addition, premature convergence of the GP may also affect classification performance. This paper proposes an archive-based multiple feature construction method which uses elite archive strategy to preserve and select effective constructed features, and employs an adaptive strategy for GP to adjust the crossover and mutation probabilities based on fitness values. Experiments on ten datasets show that our proposed archive-based multiple feature construction method without using adaptive GP can significantly improve the classification performance compared with traditional single feature construction method, and the classification performance can be maintained or further improved by adding the adaptive strategy. The comparisons with four state-of-the-art techniques show that our proposed method can significantly achieve better classification performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：