检索结果-内蒙古大学图书馆

NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models

IEEE Transactions on Big Data 2025年

作者： Mu, Lin Cheng, Yide Shen, Jun Zhang, Yiwen Zhong, Hong School of Computer Science and Technology Anhui University Anhui Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education the Anhui Engineering Laboratory of IoT Security Technologies the School of Computer Science and Technology the Institute of Physical Science and Information Technology Anhui University Hefei230039 China

Event Extraction involves extracting event-related information such as event types and event arguments from context, which has long been tackled through well-designed neural networks or fine-tuned pre-trained language models. These approaches require substantial annotated data for tuning parameters and are resource-intensive. Recently, Prompting strategies with frozen parameters, such as Chain-of-Thought and Self-Consistency, have delivered success in NLP using LLMs by generating intermediate thought steps. However, they suffer from the challenge of error propagation and lack of interaction between different thoughts. In this paper, we propose Neural Network-based Prompting (NetPrompt), a novel network-structured prompting strategy for event extraction. The core idea behind NetPrompt is to imitate the excellent information integration capabilities of neural network structures. Specifically, we first decompose the event extraction problem into diverse intermediate subtasks, and each subtask is represented as a node in different layers of the network, the output of the nodes in the preceding layer is fed into the subsequent layer. Secondly, we propose pruning strategies to adapt the reasoning overhead to different problems. Finally, we have conducted extensive experiments on two widely used event extraction benchmarks to evaluate NetPrompt. The results demonstrated that NetPrompt significantly improved the event extraction performance compared to previous methods. ©2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Homophily Induced Contrastive Attributed Graph Clustering

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China South China Technology Commercialization Center Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

Attributed graph clustering, aiming to discover the underlying graph structure and partition the graph nodes into several disjoint categories, is a basic task in graph data analysis. Although recent efforts over graph contrastive clustering have achieved decent performances, most of them get accustomed to construct the positive neighbor set by the generated pseudo clustering information, directly ignoring the ready-made neighbor nodes and the underlying semantics of edges in a graph. How to well deal with the graph neighbor-specific information to facilitate the performance of graph contrastive clustering is still a challenging problem. Therefore, in this work, we propose a novel Homophily Induced Contrastive Attributed Graph Clustering (HomoCAGC) method, where the power of homophily is exploited in facilitating the performance of contrastive attributed graph clustering, while the pseudo homophily in a graph is also explored and distinguished. Especially, the node feature as reliable information guidance is used to compute the underlying feature-oriented pair-wise node similarity, based on which the positive node pairs in contrastive regularizer are adjusted for better node representation characterization. According to the refined node representations, a triplet self-supervised clustering objective is well-designed to ensure the output embedding is cluster-oriented, and suitable for the downstream clustering task. Extensive experiments on seven benchmarks are conducted to demonstrate the effectiveness of HomoCAGC. © 1991-2012 IEEE.

关键词： Attributed graph clustering contrastive learning graph homophily self-supervised clustering

来源：评论

学校读者我要写书评

暂无评论

Carbon diffusion mechanism as an effective stability enhancement strategy:The case study of Ni-based catalyst for photothermal catalytic dry reforming of methane

引用

Chinese Journal of Catalysis 2025年第3期70卷 399-409页

作者： Dezheng Li Huimin Liu Xuewen Xiao Manqi Zhao Dehua He Yiming Lei School of Chemical and Environmental Engineering Liaoning University of TechnologyJinzhou 121000LiaoningChina Institute of Molecular Sciences of Orsay(ISMO) University Paris-Saclay and National Centre for Scientific Research(CNRS)Orsay91400France Key Laboratory of Organic Optoelectronics and Molecular Engineering of Ministry of Education Department of ChemistryTsinghua UniversityBeijing 100084China Department of Chemistry(Inorganic Chemistry) Faculty of SciencesAutonomous University of Barcelona(UAB)Cerdanyola del VallesBarcelona 08193Spain

Photothermal catalytic methane dry reforming(DRM)technology can convert greenhouse gases(***_(4)and CO_(2))into syngas(i.e.H_(2)and CO),providing more opportunities for reducing the greenhouse effect and achieving carbon *** the DRM field,Ni-based catalysts attract wide attention due to their low cost and high ***,the carbon deposition over Ni-based catalysts always leads to rapid deactivation,which is still a main *** improve the long-term stability of Ni-based catalysts,this work proposes a carbon-atom-diffusion strategy under photothermal conditions and investigates its effect on a Zn-doped Ni-based photothermal catalyst(Ni_(3)Zn@CeO_(2)).The photothermal catalytic behavior of Ni_(3)Zn@CeO_(2)can maintain more than 70 h in DRM *** the photocatalytic DRM activity of Ni_(3)Zn@CeO_(2)is 1.2 times higher than thermal catalytic *** functional theory(DFT)calculation and experimental characterizations indicate that Ni_(3)Zn promotes the diffusion of carbon atoms into the Ni_(3)Zn to form the Ni_(3)ZnC0.7 phase with body-centered cubic(bcc)structure,thus inhibiting carbon ***,in-situ diffuse reflectance infrared Fourier transform(DRIFT)spectroscopy and DFT calculation prove Ni_(3)Zn@CeO_(2)benefits the CH_(4)activation and inhibits the carbon deposition during the DRM *** inducing carbon atoms diffusion within the Ni_(3)Zn lattice,this work provides a straightforward and feasible strategy for achieving efficient photothermal catalytic DRM and even other CH_(4)conversion implementations with long-term stability.

关键词： Photothermal catalysis Methane dry reforming Ni-based catalyst Stability enhancement Carbon atom diffusion

来源：评论

学校读者我要写书评

暂无评论

From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning

arXiv

引用

arXiv 2025年

作者： Li, Ziang Zhang, Hongguang Wang, Juan Chen, Meihui Hu, Hongxin Yi, Wenzhe Xu, Xiaoyang Yang, Mengda Ma, Chenjun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Shanghai Innovation Institute China Ant Group China Department of Computer Science and Engineering University at Buffalo SUNY United States

Model Inversion Attacks (MIAs) aim to reconstruct private training data from models, leading to privacy leakage, particularly in facial recognition systems. Although many studies have enhanced the effectiveness of white-box MIAs, less attention has been paid to improving efficiency and utility under limited attacker capabilities. Existing black-box MIAs necessitate an impractical number of queries, incurring significant overhead. Therefore, we analyze the limitations of existing MIAs and introduce Surrogate Model-based Inversion with Long-tailed Enhancement (SMILE), a high-resolution oriented and query-efficient MIA for the black-box setting. We begin by analyzing the initialization of MIAs from a data distribution perspective and propose a long-tailed surrogate training method to obtain high-quality initial points. We then enhance the attack’s effectiveness by employing the gradient-free black-box optimization algorithm selected by NGOpt. Our experiments show that SMILE outperforms existing state-of-the-art black-box MIAs while requiring only about 5% of the query overhead. Our code is available at https://***/L1ziang/SMILE. Copyright © 2025, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

CPST-GAN: Conditional Probabilistic State Transition Generative Adversarial Network With the Biomedical Large Foundation Models

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年 PP卷 PP页

作者： Wang, Qiong Xu, Luyun Shan, Yinglu Shen, Wenzhuo Li, Lou Bi, Xia-An Liu, Zhonghua Hunan Normal University Key Laboratory of Computing and Stochastic Mathematics Ministry of Education School of Mathematics and Statistics College of Information Science and Engineering Changsha410081 China Hunan Normal University College of Business Changsha410081 China Hunan Normal University College of Information Science and Engineering Changsha410081 China

The risk prediction of Alzheimer's disease (AD) is crucial for its early prevention and treatment. However, current risk prediction methods face challenges in effectively extracting and fusing multiomics features, particularly overlooking the multilevel evolutionary mechanisms of AD. This article combines biomedical large foundation models with the conditional generative adversarial network (GAN) to mine the evolutionary patterns of AD by considering the regulatory effect of genes on brain lesions. Specifically, we first use biomedical large foundation models to effectively construct high-quality imaging genetic features. Next, a conditional probabilistic state transition mathematical model is constructed to describe AD progression as state transitions of brain regions under genetic regulations. Based on the mathematical model, a conditional probabilistic state transition GAN (CPST-GAN) is proposed. This algorithm can mine the dynamic evolutionary patterns of AD by fusing brain imaging and genetic features to achieve risk prediction of AD. Finally, experiments on the public imaging genetics datasets validate the effectiveness and superiority of CPST-GAN in evolutionary pattern mining and risk prediction of AD. This article not only provides a reliable intelligence algorithm for early intervention of AD but also offers new insights for future research on AD pathogenesis. The code has been published at ***/fmri123456/CPST-GAN. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC Systems

Joint DNN Partition and Thread Allocation Optimization for E...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yizhou Shi Liying Li Yue Zeng Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

关键词： Energy consumption Instruction sets Heuristic algorithms Artificial neural networks Predictive models Prediction algorithms Inference algorithms Partitioning algorithms Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Progressive Human Motion Generation Based on Text and Few Motion Frames

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zeng, Ling-An Wu, Gaojie Wu, Ancong Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Artificial Intelligence Guangdong Zhuhai519082 China Sun Yat-sen University School of Computer Science and Engineering Guangdong Guangzhou510275 China Sun Yat-sen University School of Computer Science and Engineering China Guangdong Key Laboratory of Information Security Technology China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China Peng Cheng Laboratory China

Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available here. © 1991-2012 IEEE.

关键词： Controllable Motion Generation Human Motion Text2Motion Generation

来源：评论

学校读者我要写书评

暂无评论

Dipole Antenna Arrays with Inherently High Port Isolation Levels

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Chen, Zhiyuan Lu, Dacheng Tang, Ming-Chun Hu, Kun-Zhi Li, Dajiang Liu, Heng Yi, Da Chongqing University of Posts and Telecommunications Key Laboratory of Industrial Internet of Things and Networked Control College of Automation Chongqing400065 China Chongqing University of Posts and Telecommunications Institute of Industrial Internet Chongqing China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education School of Microelectronics and Communication Engineering Chongqing400044 China

In this letter, the dipole antenna arrays with self-decoupling characteristics are developed. In comparison with the traditional electric dipole antennas, the developed dipole antenna can be considered as comprising an electric dipole and two magnetic dipoles while maintaining a relatively simple structural design. The multi-coupling cancellation between adjacent antenna elements was achieved to achieve high port isolation levels. To validate the effectiveness of the developed self-decoupling method, a 1×2 antenna array is simulated, fabricated, and measured. The results demonstrated port isolation level exceeds 25 dB over the entire operational bandwidth of 3.3-3.8 GHz, and a maximum isolation level of ⁓63 dB was achieved. Furthermore, a 1×6 antenna array is simulated to validate the extensibility of the developed self-decoupling method, where the isolation levels between all ports exceeds 25 dB across the entire operational bandwidth of 3.3-3.8 GHz. © 2002-2011 IEEE.

关键词： Structural dynamics

来源：评论

学校读者我要写书评

暂无评论

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation

arXiv

引用

arXiv 2025年

作者： Zhang, Shenyi Zhai, Yuchen Guo, keyan Hu, Hongxin Guo, Shengnan Fang, Zheng Zhao, Lingchen Shen, Chao Wang, Cong Wang, Qian Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China University at Buffalo United States Xi’an Jiaotong University China City University of Hong Kong Hong Kong

Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed to detect or mitigate jailbreaks, but they are unable to withstand the test of time due to an insufficient understanding of jailbreak mechanisms. In this work, we investigate the mechanisms behind jailbreaks based on the Linear Representation Hypothesis (LRH), which states that neural networks encode high-level concepts as subspaces in their hidden representations. We define the toxic semantics in harmful and jailbreak prompts as toxic concepts and describe the semantics in jailbreak prompts that manipulate LLMs to comply with unsafe requests as jailbreak concepts. Through concept extraction and analysis, we reveal that LLMs can recognize the toxic concepts in both harmful and jailbreak prompts. However, unlike harmful prompts, jailbreak prompts activate the jailbreak concepts and alter the LLM output from rejection to compliance. Building on our analysis, we propose a comprehensive jailbreak defense framework, JBSHIELD, consisting of two key components: jailbreak detection JBSHIELD-D and mitigation JBSHIELD-M. JBSHIELD-D identifies jailbreak prompts by determining whether the input activates both toxic and jailbreak concepts. When a jailbreak prompt is detected, JBSHIELD-M adjusts the hidden representations of the target LLM by enhancing the toxic concept and weakening the jailbreak concept, ensuring LLMs produce safe content. Extensive experiments demonstrate the superior performance of JBSHIELD, achieving an average detection accuracy of 0.95 and reducing the average attack success rate of various jailbreak attacks to 2% from 61% across distinct LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimal Flying Location for Unmanned Aerial Vehicle Equipped with MF-RIS assisted Covert Wireless on Communication

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Jie Li, Yunxiang Tian, Wen Dai, Yuewei Liu, Yinqiu Niyato, Dusit Nanjing University of Posts and Telecommunications School of Communications and Information Engineering Nanjing China Nanjing University of Information Science and Technology School of Electronic and Information Engineering Key Laboratory of Intelligent Support Technology In Complex Environment Ministry of Education Nanjing210044 China Nanyang Technological University College of Computing and Data Science Singapore

In the current information age, covert communication holds significant value owing to its advantages, such as heightened security, enhanced flexibility, and improved concealment, surpassing those of traditional communication methods. However, existing covert communication approaches approximate communication channel models by Line-of-Sight (LoS) links, which is insufficient due to neglecting the impact of multipath effects and applying inaccurate performance assessments. To better adapt to real-world communication channel conditions, we propose a novel covert communication model assisted by Unmanned Aerial Vehicles (UAV) equipped with Multi-Functional Reconfigurable Intelligent Surface (MF-RIS), named UMCCM. Specifically, based on a mixed link of LoS and Non-Line-of-Sight (NLoS), UMCCM leverages MF-RIS as a flexible relay to enhance the signal-to-noise ratio (SNR) and effective throughput. We first derive the mixed channel model expression. Then, we transform covert constraints from incomplete gamma functions to those linked with relative entropy and accordingly optimize the UAV transmission power and block length. Finally, the optimal flying position of the UAV is obtained by analyzing the functional properties of SNR and effective throughput under these refined constraints. Extensive numerical results demonstrate the superiority of our proposed UMCCM for enhancing SNR and effective throughput over the existing works. © 2025 IEEE.

关键词： Aircraft communication

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：