检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Chen, Zhijun Li, Jingzheng Chen, Pengpeng Li, Zhuoran Sun, Kai Luo, Yuankai Mao, Qianren Yang, Dingqi Sun, Hailong Yu, Philip S. State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Zhongguancun Laboratory Beijing China Aviation System Engineering Institute of China Beijing China Xi’an Jiaotong University Xi’an China University of Macau China University of Illinois at Chicago Chicago United States

LLM Ensemble—which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths—has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of "ensemble-before-inference, ensemble-during-inference, ensemble-after-inference", and review all relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest several future research directions. A curated list of papers on LLM Ensemble is available at https://***/junchenzhi/ Awesome-LLM-Ensemble. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing

arXiv

引用

arXiv 2025年

作者： Zhang, Yuwei Jin, Zhi Xing, Ying Li, Ge Liu, Fang Zhu, Jiaxin Dou, Wensheng Wei, Jun Affiliated with Nanjing Institute of Software Technology University of Chinese Academy of Sciences Nanjing China Key Laboratory of System Software Chinese Academy of Sciences Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Computer Science Wuhan University Wuhan China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a noticeable gap in existing approaches lies in the oversight of collaborative facets intrinsic to bug resolution, treating the process as a single-stage endeavor. Moreover, most approaches solely take the buggy code snippet as input for LLMs during the patch generation stage. To mitigate the aforementioned limitations, we introduce a novel stage-wise framework named PATCH. Specifically, we first augment the buggy code snippet with corresponding dependence context and intent information to better guide LLMs in generating the correct candidate patches. Additionally, by taking inspiration from bug management practices, we decompose the bug-fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to simulate the collaborative behavior of programmers during the resolution of software bugs. By harnessing these collective contributions, PATCH effectively enhances the bug-fixing capability of LLMs. We implement PATCH by employing the powerful dialogue-based LLM ChatGPT. Our evaluation on the widely used bug-fixing benchmark BFP demonstrates that PATCH has achieved better performance than state-of-the-art LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： Computer software maintenance

来源：评论

学校读者我要写书评

暂无评论

A Novel Rolling Bearing Vibration Impulsive Signals Detection Approach Based on Dictionary Learning

引用

IEEE/CAA Journal of Automatica Sinica 2021年第6期8卷 1188-1198页

作者： Chuan Sun Hongpeng Yin Yanxia Li Yi Chai School of Big Data&Software Engineering Chongqing UniversityChongqing 401331China Key Laboratory of Complex System Safety and Control Ministry of EducationChongqing UniversityChongqing 400044China

The localized faults of rolling bearings can be diagnosed by its vibration impulsive ***,it is always a challenge to extract the impulsive feature under background noise and non-stationary *** paper investigates impulsive signals detection of a single-point defect rolling bearing and presents a novel data-driven detection approach based on dictionary *** overcome the effects harmonic and noise components,we propose an autoregressive-minimum entropy deconvolution model to separate harmonic and deconvolve the effect of the transmission *** address the shortcomings of conventional sparse representation under the changeable operation environment,we propose an approach that combines K-clustering with singular value decomposition(K-SVD)and split-Bregman to extract impulsive components *** experiments on synthetic signals and real run-to-failure signals,the excellent performance for different impulsive signals detection verifies the effectiveness and robustness of the proposed ***,a comparison with the state-of-the-art methods is illustrated,which shows that the proposed approach can provide more accurate detected impulsive signals.

关键词： Dictionary learning impulsive signals detection Kclustering with singular value decomposition(K-SVD) minimum entropy deconvolution rolling bearing signal processing

来源：评论

学校读者我要写书评

暂无评论

Jointgraph: A DAG-based efficient consensus algorithm for consortium blockchains

Jointgraph: A DAG-based efficient consensus algorithm for co...

引用

作者： Xiang, Fu Huaimin, Wang Peichang, Shi Xue, Ouyang Xunhui, Zhang School of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex System Changsha China

The blockchain is a distributed ledger that records all transactions and operations in a shared manner. Public blockchains such as Bitcoin realize decentralization at the cost of mining overhead, which is not suitable for real-life scenarios requiring high throughput. Techniques such as the consortium blockchain improve efficiency through partial decentralization. However, the consensus algorithms used in the existing state-of-the-art consortium blockchains face many challenges when dealing with commercial applications. For example, the high communication overhead hinders the scalability of PBFT-based consensus algorithms even though they are efficient at small scale. Hashgraph, one of the most popular Directed Acyclic Graph-based (DAG-based) consensus algorithms, achieves good performance in scalability;however, it does not allow users' dynamic participation. To deal with these challenges, we propose Jointgraph, a Byzantine fault-tolerance consensus algorithm for consortium blockchains based on DAG. In Jointgraph, transactions are packed into events and validated by no less than 2/3 of all members. A supervisor is introduced in our design, who monitors member behaviors and improves consensus efficiency. Simulation results demonstrate that Jointgraph outperforms Hashgraph in both throughput and latency. © 2019 John Wiley & Sons, Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

AN IMPROVED STRUCTURED MESH GENERATION METHOD BASED ON PHYSICS-INFORMED NEURAL NETWORKS

arXiv

引用

arXiv 2022年

作者： Chen, Xinhai Liu, Jie Yan, Junjun Wang, Zhichao Gong, Chunye Laboratory of Software Engineering for Complex System National University of Defense Technology Changsha China

Mesh generation remains a key technology in many areas where numerical simulations are required. As numerical algorithms become more efficient and computers become more powerful, the percentage of time devoted to mesh generation becomes higher. In this paper, we present an improved structured mesh generation method. The method formulates the meshing problem as a global optimization problem related to a physics-informed neural network. The mesh is obtained by intelligently solving the physical boundary-constrained partial differential equations. To improve the prediction accuracy of the neural network, we also introduce a novel auxiliary line strategy and an efficient network model during meshing. The strategy first employs a priori auxiliary lines to provide ground truth data and then uses these data to construct a loss term to better constrain the convergence of the subsequent training. The experimental results indicate that the proposed method is effective and robust. It can accurately approximate the mapping (transformation) from the computational domain to the physical domain and enable fast high-quality structured mesh generation. Copyright © 2022, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Application of PID parameters optimization based on GWO in mould level system

Application of PID parameters optimization based on GWO in m...

引用

2021 International Conference on Internet, Education and Information Technology, IEIT 2021

作者： Sitong, Liu Xiangwei, Kong Peifeng, Hao Hezhan, Gao Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Shenyang China

ISBN: (纸本)9781665425636

Mold level stability is a very important factor in the continuous casting process. To effectively control the liquid level at the set value, solve the problems of disturbance, nonlinearity, and time-varying in the system, as well as modeling difficulties caused by uncertain factors, and aiming at the shortcomings of conventional PID control, the gray wolf algorithm is introduced the gray wolf optimization algorithm is used to self-tune the PID parameters, and the objective function is constructed based on the adjustment time and steady-state error of the mold liquid level system. Finally, the simulation and experimental results show that the algorithm optimization proposed in this paper is compared with the particle swarm algorithm, and the step response of the system is smoother. Gray Wolf optimized PID control has a fast response speed, with an adjustment time of 3.87s, which is lower than 13.46s for conventional PID control and 5.58s for the PSO algorithm. It can significantly improve the control accuracy and other performance indicators of the system. It provides a reference for improving the level control of the continuous casting mold. © 2021 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

PID Parameter Optimization of Secondary Cooling Water Distribution Model for Continuous Casting Based on Improved Artificial Bee Colony Algorithm 4

PID Parameter Optimization of Secondary Cooling Water Distri...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Wang, Yibing Kong, Xiangwei Hao, Peifeng Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Shenyang China

ISBN: (纸本)9780738131702

Dynamic control of secondary cooling in continuous casting is the key technology to improve the quality and efficiency of the slab. In order to improve the quality and efficiency of the slab, a new control strategy of secondary cooling water distribution based on an improved artificial bee colony algorithm is proposed. Based on the traditional artificial bee colony algorithm, adding the learning factor to the optimal individual learning factor and random individual of the current population and integrating the output overshoot mechanism into the objective function is effective to avoid the great overshoot phenomenon caused by the abruptly change of casting speed and the large fluctuation of casting surface temperature. The transfer function was constructed based on the coupling relationship between the distribution of secondary cooling water and slab surface temperature. The Simulink simulation model was established, which was compared with the PSO-DSWPI Method and conventional PID controller. The results showed that the improved artificial bee colony algorithm has a more minor error, higher control accuracy and more smooth step response, which provided a new method for realizing more accurate control of secondary cooling dynamic water distribution and had practical significance for improving slab quality. © 2021 IEEE.

关键词： Cooling water

来源：评论

学校读者我要写书评

暂无评论

Few-shot Learning for Rolling Bearing Fault Diagnosis Based on Residual Convolutional Neural Network 4

Few-shot Learning for Rolling Bearing Fault Diagnosis Based ...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Cui, Zihao Kong, Xiangwei Hao, Peifeng Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Shenyang China

ISBN: (纸本)9780738131702

This paper proposes a new Siamese network model for fault diagnosis with limited training samples. We introduce residual blocks to the Siamese network model for few-shot learning. By using the same or different types of sample pairs to learn, our model further improves the accuracy of the Siamese network in bearing fault diagnosis under different workloads and noisy environments. Experiments on the CWRU and MFPT data set showed that the proposed model outperforms the convolutional Siamese network in bearing fault diagnosis. The accuracy of our model has achieved more than 93% accuracy with 90 training samples on the CWRU and MFPT data set. All our models and experiments are available from https://***/WunaiDczh/Few_data_Learing. © 2021 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

An unsupervised deep learning framework for gene regulatory network inference from single-cell expression data

An unsupervised deep learning framework for gene regulatory ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Mao, Guo Liu, Jie National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha410073 China National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Laboratory of Software Engineering for Complex System Changsha410073 China

ISBN: (纸本)9798350337488

Recent advances in single-cell RNA sequencing (scRNA-seq) technology provides unprecedented opportunities for reconstruction gene regulation networks (GRNs). At present, many different models have been proposed to infer GRN from a large number of RNA-seq data, but most deep learning models use a priori gene regulatory network to infer potential GRNs. It is a challenge to reconstruct GRNs from scRNA-seq data due to the noise and sparsity introduced by the dropout effect. Here, we propose GAALink, a novel unsupervised deep learning method. It first constructs the gene similarity matrix and then refines it by threshold value. It then learns feature representations of genes through a graphical attention autoencoder that propagates information across genes with different weights. Finally, we use gene feature expression for matrix completion such that the GRNs are reconstructed. Compared with seven existing GRNs reconstruction methods, GAALink achieves more accurate performance on seven scRNA-seq dataset with four ground truth networks. GAALink can provide a useful tool for inferring GRNs for scRNA-seq expression data. © 2023 IEEE.

关键词： Feature representations Gene similarity matrix Graphical attention autoencoder Matrix completion Unsupervised deep learning method

来源：评论

学校读者我要写书评

暂无评论

Repulsive Particle Swarm Optimization Based on New Diversity

Repulsive Particle Swarm Optimization Based on New Diversity

引用

The 22nd China Control and Decision Conference(2010年中国控制与决策会议)

作者： Guochao Niu Baodi Chen Jianchao Zeng Software Engineering Institute Xidian University Xi'an 710071China Software Engineering Institute Xidian University Xi'an 710071China Complex System and Computation Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technolo

ISBN: (纸本)9781424451814;9781424451821

To avoid the problem of premature convergence, a new diversity-guided Particle Swarm Optimizer (PSO), namely MARPSO is proposed, which is a modification of attractive and repulsive PSO (ARPSO), suggested by Riget and Vesterstorm[1]. A novel measure of population diversity function is presented and a new concept of the particles best flight direction is introduced. The simulation test results of four classic functions show that: compared with Standard PSO (BPSO) and ARPSO, MARPSO can effectively increase the diversity of swarm, while maintain a higher convergence speed.

关键词： Particle Swarm Optimization Population Diversity Global Search Particle's Best Flight Direction

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：