检索结果-内蒙古大学图书馆

A Systematic Literature Review on Large Language Models for Automated Program Repair

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Quanjun Fang, Chunrong Xie, Yang Ma, Yuxiang Sun, Weisong Yang, Yun Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Technologies Swinburne University of Technology Australia

Automated Program Repair (APR) attempts to patch software bugs and reduce manual debugging efforts. Very recently, with the advances in Large Language Models (LLMs), a rapidly increasing number of APR techniques have been proposed, significantly facilitating software development and maintenance and demonstrating remarkable performance. However, due to ongoing explorations in the LLM-based APR field, it is challenging for researchers to understand the current achievements, challenges, and potential opportunities. This work provides the first systematic literature review to summarize the applications of LLMs in APR between 2020 and 2024. We analyze 127 relevant papers from LLMs, APR and their integration perspectives. First, we categorize existing popular LLMs that are applied to support APR and outline three types of utilization strategies for their deployment. Besides, we detail some specific repair scenarios that benefit from LLMs, e.g., semantic bugs and security vulnerabilities. Furthermore, we discuss several critical aspects of integrating LLMs into APR research, e.g., input forms and open science. Finally, we highlight a set of challenges remaining to be investigated and the potential guidelines for future research. Overall, our paper provides a systematic overview of the research landscape to the APR community, helping researchers gain a comprehensive understanding of achievements and promote future research. Our artifacts are publicly available at the GitHub repository: https://***/iSEngLab/AwesomeLLM4APR. © 2024, CC BY.

关键词： Repair

Resource Allocation Driven by Large Models in Future Semantic-Aware Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Haijun Ni, Jiaxin Wu, Zijun Liu, Xiangnan Leung, V.C.M. Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing10083 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden College of Computer Science and Software Engineering Shenzhen University Shenzhen51806 China VancouverBCV6T 1Z4 Canada

Large model has emerged as a key enabler for the popularity of future networked intelligent applications. However, the surge of data traffic brought by intelligent applications puts pressure on the resource utilization and energy consumption of the future networks. With efficient content understanding capabilities, semantic communication holds significant potential for reducing data transmission in intelligent applications. In this article, resource allocation driven by large models in semantic-aware networks is investigated. Specifically, a semantic-aware communication network architecture based on scene graph models and multimodal pre-trained models is designed to achieve efficient data transmission. On the basis of the proposed network architecture, an intelligent resource allocation scheme in semantic-aware network is proposed to further enhance resource utilization efficiency. In the resource allocation scheme, the semantic transmission quality is adopted as an evaluation metric and the impact of wireless channel fading on semantic transmission is analyzed. To maximize the semantic transmission quality for multiple users, a diffusion model-based decision-making scheme is designed to address the power allocation problem in semantic-aware networks. Simulation results demonstrate that the proposed large-model-driven network architecture and resource allocation scheme achieve high-quality semantic transmission. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Web

Research on Crop Planting Strategies Based on NSGA-2 and Bi-level Robust Optimization 24

学校读者我要写书评

暂无评论

Research on Crop Planting Strategies Based on NSGA-2 and Bi-...

Proceedings of the 2024 4th International Conference on Computational Modeling, Simulation and Data Analysis

作者： Qing Zhang Xiaoqiang Qiu Ke Li Mingyu Dong Miaomiao Qiao Dun Liu Zhikun Zhang School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou Henan China School Of Mechanical And Power Engineering Zhengzhou University Zhengzhou Henan China School of Software Nanyang Institute of Technique Nanyang Henan China Business School Zhengzhou University Zhengzhou Henan China

ISBN: (纸本)9798400711831

Making full use of limited farmland resources, selecting suitable crops, optimizing planting schemes, and developing modern agriculture have great practical significance for rural economic development. In this paper, we focus on answering a key question: given the uncertainties in expected sales, yield per mu, planting costs, sales prices, and potential planting risks of various crops, what is the optimal crop planting plan for the village from 2024 to 2030? We adopt the breakeven point and safety margin ratio from economic theory, combined with the 2023 crop yields, to define the expected sales volumes. Additionally, we use the entropy weight method-evaluation model to score crops on different plots and construct an objective function to maximize planting scores. At the same time, we also establish an objective function to maximize rural planting profits. This paper employs a two-layer robust optimization model based on the outer-layer NSGA-2 non-dominated sorting genetic algorithm and the inner-layer simulated annealing algorithm to solve the multi-objective programming problem in an uncertain environment. Among the Pareto-optimal solutions, we find the optimal solution using the evaluation model. The outer-layer NSGA-2 seeks to maximize profits, while the inner-layer simulated annealing algorithm seeks to minimize profits, thus maximizing the minimum profit and obtaining an optimal robust solution capable of addressing the maximum risk. This solution yields a profit of 33.0674 million yuan and a planting score of 450.67 in the worst uncertainty scenario. The research results show that the optimal robust solution obtained by this method has high profits and can effectively address market uncertainty risks.

关键词： Crop planting strategies

On Efficient Packet Batching and Resource Allocation for GPU based NFV Acceleration

学校读者我要写书评

暂无评论

On Efficient Packet Batching and Resource Allocation for GPU...

International Workshop on Quality of Service

作者： Deze Zeng Andong Zhu Lin Gu Quan Chen Minyi Guo School of Computer Science China University of Geosciences Wuhan Hubei China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Network Function Virtualization (NFV) has already become an essential technology for improving the scalability and flexibility of modern computer networks. The performance gap has become the main issue that impedes the development of NFV. GPUs, with massive parallel processors, are advocated to accelerate the Virtualized Network Functions (VNFs). However, the special architecture and workflow of GPUs introduce new challenges, especially on the batched processing, and resource allocation. In this paper, we propose GPU-based NFV Acceleration framework (GNFA) with an efficient packet batching and resource allocation solution. Considering the increased latency caused by the accumulation of the GPU kernel invoking overhead, we first invent a latency reduction mechanism called SM Performance Compensation (SPC). A Partition and Adjustment based Batching and Resource Allocation (PABARA) algorithm that jointly considers batch size tuning and GPU thread allocation is also proposed. We have practically implemented GNFA and extensively evaluated its performance on some well-known VNFs. The experiment results show that GNFA can effectively promote the GPU resource utilization and improve the NFV performance in terms of per-packet latency.

关键词：

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Song, Weixi Li, Zuchao Zhang, Lefei Zhao, Hai Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Luojia Laboratory Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscillations in the loss landscape and the quasi-sparsity in gradient distribution. Based on this, we propose a gradient-based sparse finetuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://***/song-wx/SIFT. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Image Reconstruction Improvement of Variable Coded Aperture Using Deep Learning Method for Gamma and Lensless Imaging Applications

学校读者我要写书评

暂无评论

Image Reconstruction Improvement of Variable Coded Aperture ...

Conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Ariel Schwarz Amir Shemer Eliezer Danan Noa E. Cohen Yossef Danan Department of Electrical and Electronics Engineering Azrieli College of Engineering Jerusalem Israel Faculty of Engineering Bar-Ilan University Ramat-Gan Israel School of Software Engineering and Computer Science Azrieli College of Engineering Jerusalem Israel

ISBN: (纸本)9798350345995

In gamma ray imaging for nuclear medicine, coded aperture is used to improve sensitivity. one of the main reconstructing methods is inverse filtering (deconvolution), where the recorded image is cross-correlated with periodic inverse filter of coded array. The reconstruction is free of coding noise for arbitrary array. However, amplification of quantum noise affect the reconstructed image. Although it is improved by Wiener filtering, the major problem is small terms in the spectral distribution of coded masks. Statistically and experimentally pinhole arrays have at least one term which is zero, resulting unacceptably noisy reconstruction. In our previous research we presented new approach of variable coded aperture (VCA) design for far and near field imaging applications [1–4]. The imaging system is based on time multiplexing method using variable multi pinhole array. The unique variable design enables to overcome the spatial frequencies cutoff and small terms in the Fourier transform exists in static multi pinhole array. The overall pinholes positions are designed to avoid spatial frequencies loss. However, traces of duplications can still be detected in reconstruction using Wiener filtering. Furthermore, since coded aperture blocks most of the photons that enter the detector, the dynamic range of the image is limited, thus leading to low contrast image and inadequate colors gamut.

关键词： Deep learning Fourier transforms Image metrics Imaging systems Quantum noise Spatial frequency

A New Identity-Based Encryption Scheme with Accountable Authority Based on SM9 11

学校读者我要写书评

暂无评论

A New Identity-Based Encryption Scheme with Accountable Auth...

11th International Conference on Electronics, Communications and Networks, CECNet 2021

作者： Wang, Ke Zhao, Yuan Luo, Song Guan, Zhi MoE Beijing China Department of Computer Science and Technology EECS Peking University Beijing China School of Computer Science and Engineering Chongqing University of Technology Chongqing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (纸本)9781643682402

Accountable authority identity-based encryption (A-IBE) is an extension of identity-based encryption (IBE) in which private key's source can be traced, i.e., whether the key comes from a private key generator or a user. SM9 is an official cryptography standard of China which defines a practical IBE scheme. In this paper, we construct a practical A-IBE scheme from the SM9-IBE scheme. Our A-IBE scheme has public traceability and is proven secure if the based SM9-IBE scheme is secure. Compared with other A-IBE schemes, our A-IBE scheme has better efficiency in encryption and decryption. © 2022 The authors and IOS Press.

关键词： Cryptography

CS-Net: Contribution-based Sampling Network for Point Cloud Simplification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Guo, Tian Chen, Chen Yuan, Hui Mao, Xiaolong Hamzaoui, Raouf Hou, Junhui School of Control Science and Engineering Shandong University Ji’nan250061 China School of Software Shandong University Ji’nan250061 China School of Engineering and Sustainable Development De Montfort University LeicesterLE1 9BH United Kingdom Department of Computer Science City University of Hong Kong Hong Kong

Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information and, as a result, cannot guarantee optimal performance in specific applications. Learning-based methods train a network to sample the point cloud for the targeted downstream task. However, they do not guarantee that the sampled points are the most relevant ones. Moreover, they may result in duplicate sampled points, which requires completion of the sampled point cloud through post-processing techniques. To address these limitations, we propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation. To ensure that the network can be trained in an end-to-end way using gradient descent algorithms, we use a differentiable approximation to the Top-k operation via entropy regularization of an optimal transport problem. Our network consists of a feature embedding module, a cascade attention module, and a contribution scoring module. The feature embedding module includes a specifically designed spatial pooling layer to reduce parameters while preserving important features. The cascade attention module combines the outputs of three skip connected offset attention layers to emphasize the attractive features and suppress less important ones. The contribution scoring module generates a contribution score for each point and guides the sampling process to prioritize the most important ones. Experiments on the ModelNet40 and PU147 showed that CS-Net achieved state-of-the-art performance in two semantic-based downstream tasks (classification and registration) and two reconstruction-based tasks (compression and surface reconstruction). CS-Net also achieved high average precision for objection detection on the KITTI LiDAR point cloud dataset, demonstrating its effectiveness in three-dimensional object detection. Co

关键词： Importance sampling

Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Miao, Bo Bennamoun, Mohammed Gao, Yongsheng Shah, Mubarak Mian, Ajmal The Department of Computer Science and Software Engineering The University of Western Australia Perth CrawleyWA6009 Australia The School of Engineering Griffith University BrisbaneQLD4111 Australia The Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%). The code is available at https://***/bo-miao/HTR. © 2024, CC BY.

关键词： Video analysis