检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhao, Shiju Hu, Junhao Huang, Rongxiao Zheng, Jiaqi Chen, Guihai State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science Peking University Peking China

The context caching technique is employed to accelerate the Multimodal Large Language Model (MLLM) inference by prevailing serving platforms currently. However, this approach merely reuses the key-Value (KV) cache of the initial sequence of prompt, resulting in full KV cache recomputation even if the prefix differs slightly. This becomes particularly inefficient in the context of interleaved text and images, as well as multimodal retrieval-augmented generation. This paper proposes position-independent caching as a more effective approach for multimodal information management. We have designed and implemented a caching system, named MPIC, to address both system-level and algorithm-level challenges. MPIC stores the KV cache on local or remote disks when receiving multimodal data, and calculates and loads the KV cache in parallel during inference. To mitigate accuracy degradation, we have incorporated integrated reuse and recompute mechanisms within the system. The experimental results demonstrate that MPIC can achieve up to 54% reduction in response time compared to existing context caching systems, while maintaining negligible or no accuracy loss. © 2025, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Quantum Annealing for Quadratic Unconstrained Binary Optimization (QUBO) Problems

arXiv

引用

arXiv 2024年

作者： Xie, Moyang Zhang, Yuan Zhong, Sheng Li, Qun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science William & Mary WilliamsburgVA United States

Quantum annealers offer a promising approach to solve Quadratic Unconstrained Binary Optimization (QUBO) problems, which have a wide range of applications. However, when a user submits its QUBO problem to a third-party quantum annealer, the problem itself may disclose the user's private information to the quantum annealing service provider. To mitigate this risk, we introduce a privacy-preserving QUBO framework and propose a novel solution method. Our approach employs a combination of digit-wise splitting and matrix permutation to obfuscate the QUBO problem's model matrix Q, effectively concealing the matrix elements. In addition, based on the solution to the obfuscated version of the QUBO problem, we can reconstruct the solution to the original problem with high accuracy. Theoretical analysis and empirical tests confirm the efficacy and efficiency of our proposed technique, demonstrating its potential for preserving user privacy in quantum annealing services. © 2024, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Compressing Model with Few Class-Imbalance Samples: An Out-of-Distribution Expedition

arXiv

引用

arXiv 2025年

作者： Wu, Tian-Shuang Lyu, Shen-Huan Chen, Ning Qu, Zhihao Ye, Baoliu Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In recent years, as a compromise between privacy and performance, few-sample model compression has been widely adopted to deal with limited data resulting from privacy and security concerns. However, when the number of available samples is extremely limited, class imbalance becomes a common and tricky problem. Achieving an equal number of samples across all classes is often costly and impractical in real-world applications, and previous studies on few-sample model compression have mostly ignored this significant issue. Our experiments comprehensively demonstrate that class imbalance negatively affects the overall performance of few-sample model compression methods. To address this problem, we propose a novel and adaptive framework named OOD-Enhanced Few-Sample Model Compression (OE-FSMC). This framework integrates easily accessible out-of-distribution (OOD) data into both the compression and fine-tuning processes, effectively rebalancing the training distribution. We also incorporate a joint distillation loss and a regularization term to reduce the risk of the model overfitting to the OOD data. Extensive experiments on multiple benchmark datasets show that our framework can be seamlessly incorporated into existing few-sample model compression methods, effectively mitigating the accuracy degradation caused by class imbalance. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

ATOM: Automated Black-Box Testing of Multi-Label Image Classification Systems 23

ATOM: Automated Black-Box Testing of Multi-Label Image Class...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated software Engineering

作者： Shengyou Hu Huayao Wu Peng Wang Jing Chang Yongjun Tu Xiu Jiang Xintao Niu Changhai Nie State Key Laboratory for Novel Software Technology and Department of Computer Science and Technology Nanjing University China Guangdong OPPO Mobile Telecommunications Corp. Ltd. China

ISBN: (纸本)9798350329964

Multi-label Image Classification Systems (MICSs) developed based on Deep Neural Networks (DNNs) are extensively used in people's daily life. Currently, although there are a variety of approaches to test DNN-based systems, they typically rely on the internals of DNNs to design test cases, and do not take the core specification of MICS (i.e., correctly recognizing multiple objects in a given image) into account. In this paper, we propose ATOM, an automated and systematic black-box testing framework for testing MICS. Specifically, ATOM exploits the label combination as the testing adequacy criteria, hoping to systematically examine the impact of correlations between a fixed number of labels on the classification ability of MICS. Then, ATOM leverages image search engine and natural language processing to find test images that are not only common to the real-world, but also relevant to target label combinations. Finally, ATOM combines metamorphic testing and label information to realize test oracle identification, based on which the ability of MICS in classifying different label combinations is evaluated. To evaluate the effectiveness of ATOM, we have performed experiments on two popular datasets of MICS, VOC and COCO (each with five state-of-the-art DNN models), and one real-world photo tagging application from our industrial partner. The experimental results reveal that the performance of current DNN-based MICSs remains less satisfactory even in recognizing correlations between only two labels, as ATOM triggers a total number of 6,049 such label combination related errors for all MICSs studied. In particular, ATOM reports 587 error-revealing images for the industrial MICS, in which 92% of them are confirmed by the developers.

关键词： multi-label image classification testing

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Model-based Actionable Warning Identification: A Feasibility Study

arXiv

引用

arXiv 2024年

作者： Ge, Xiuting Fang, Chunrong Zhang, Quanjun Wu, Daoyuan Yu, Bowen Zheng, Qirui Guo, An Lin, Shangwei Zhao, Zhihong Liu, Yang Chen, Zhenyu The State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Nanyang Technological University Singapore

Actionable Warning Identification (AWI) plays a pivotal role in improving the usability of static code analyzers. Currently, Machine Learning (ML)-based AWI approaches, which mainly learn an AWI classifier from labeled warnings, are notably common. However, these approaches still face the problem of restricted performance due to the direct reliance on a limited number of labeled warnings to develop a classifier. Very recently, Pre-Trained Models (PTMs), which have been trained through billions of text/code tokens and demonstrated substantial success applications on various code-related tasks, could potentially circumvent the above problem. Nevertheless, the performance of PTMs on AWI has not been systematically investigated, leaving a gap in understanding their pros and cons. In this paper, we are the first to explore the feasibility of applying various PTMs for AWI. By conducting the extensive evaluation on 10K+ SpotBugs warnings from 10 large-scale and open-source projects, we observe that all studied PTMs are consistently 9.85%∼21.12% better than the state-of-the-art ML-based AWI approaches. Besides, we investigate the impact of three primary aspects (i.e., data preprocessing, model training, and model prediction) in the typical PTM-based AWI workflow. Further, we identify the reasons for current PTMs’ underperformance on AWI. Based on our findings, we provide several practical guidelines to enhance PTM-based AWI in future work. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Bao, Yanqi Ding, Tianyu Huo, Jing Liu, Yaoli Li, Yuxin Li, Wenbin Gao, Yang Luo, Jiebo Nanjing University State Key Laboratory for Novel Software Technology 210023 China Microsoft Corporation Applied Sciences Group Redmond United States University of Rochester Department of Computer Science United States

3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations. It can effectively transform multi-view images into explicit 3D Gaussian through efficient training, and achieve real-time rendering of novel views. This survey aims to analyze existing 3DGS-related works from multiple intersecting perspectives, including related tasks, technologies, challenges, and opportunities. The primary objective is to provide newcomers with a rapid understanding of the field and to assist researchers in methodically organizing existing technologies and challenges. Specifically, we delve into the optimization, application, and extension of 3DGS, categorizing them based on their focuses or motivations. Additionally, we summarize and classify nine types of technical modules and corresponding improvements identified in existing works. Based on these analyses, we further examine the common challenges and technologies across various tasks, proposing potential research opportunities. © 1991-2012 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-objective software test case selection based on density analysis 22

Multi-objective software test case selection based on densit...

引用

5th International Conference on computer science and software Engineering, CSSE 2022

作者： Jia, Huihui Zhang, Cheng Wu, Sijie Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University China School of Computer Science and Technology Anhui University China State Key Lab for Novel Software Technology Nanjing University Hefei China

ISBN: (纸本)9781450397780

software test case selection is committed to select the fewest test cases from test suites to perform a complete test at the least cost. Machine learning and multi-objective optimization techniques have developed rapidly in recent years, and they have been successfully applied to test case selection. In this paper, we present a method called DB-NSGA2, which uses the density clustering algorithm in machine learning combined with the non-dominated ranking algorithm (NSGA2) for test case selection, which can better select the test cases required for testing. In particular, we apply some of the clustering results generated by the clustering algorithm to the crossover and mutation operations of the NSGA2 to improve diversity progeny populations and ensure the transmission of good individuals. Extensive experiments show that the test cases selected by our method can produce a better set of Pareto solutions and can detect more faults at a lower cost than other methods. © 2022 ACM.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Decoding Issue Dynamics: A novel Approach for Identifying Issue Linkages in Github Projects

SSRN

引用

SSRN 2024年

作者： Yang, Wenhua He, Yingying Pan, Minxue Zhou, Yu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

GitHub serves as a pivotal platform for open-source software development, where effective issue management is crucial for project success. Despite its importance, current tools in GitHub fall short in identifying interconnections among issues, a key component for efficient management. This paper addresses the challenge of detecting and classifying linkages between issues in GitHub, which is hindered by the platform's rudimentary linkage features. We introduce a novel two-stage machine learning approach that first ascertains the presence of linkages using a lightweight binary classifier and then classifies their types with a detailed multi-classifier. Our approach leverages existing issue data to enhance linkage detection, thereby facilitating better management practices by categorizing issue relations and prioritizing development efforts. This approach not only refines issue linkage identification but also optimizes computational resources by focusing detailed analysis on a filtered subset of linked issues. We demonstrate the effectiveness of our approach through comparative studies and highlight its potential for improving issue tracking in large-scale GitHub projects. © 2024, 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

Deploying Wireless-Powered UAV Base Stations for Maximizing Throughput

Deploying Wireless-Powered UAV Base Stations for Maximizing ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Xiang Chen Xiaoyu Wang He Huang Haipeng Dai School of Computer Science and Technology Soochow University Suzhou Jiangsu China State Key Laboratory for Novel Software Technology Nanjing University Nanjing Jiangsu China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Unmanned Aerial Vehicle (UAV) mounted base stations have been widely used to enhance the existing terrestrial communication infrastructures. In this paper, we investigate the problem of deploying Wireless-Powered UAV base stations (UAV-BSs) for maximizing Throughput (WPUT), that is, deploying a specified number of UAV base stations, which can harvest power from Wireless Charging Towers (WCTs), to maximize the total throughput for all users under the constraint of providing communication service continuously with the wireless power. To address the problem, we first approximate the nonlinear charging power as a piecewise constant function while bounding the approximation error. Then the entire region is divided into different charging subareas for the UAVs. Furthermore, we discretize the subareas by another piecewise constant function to approximate the communication rate with error bound. Finally, the problem is transformed into a 0–1 integer programming problem. We apply the primal-dual technique to deal with the problem after LP-relaxation and achieve a $\frac{1}{(1+\epsilon)^{2}}$ -approximation algorithm. Simulation results show that our proposed algorithm can outperform comparison algorithms by 36.92% on average.

关键词： Wireless communication Integer programming Base stations Simulation Poles and towers Inductive charging Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Identification of Microservices through Processed Dynamic Traces and Static Calls 3

Identification of Microservices through Processed Dynamic Tr...

引用

3rd International Conference on computer science and Management technology, ICCSMT 2022

作者： Wu, Sijie Zhang, Cheng Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University China Anhui University School of Computer Science and Technology China Nanjing University State Key Lab for Novel Software Technology Hefei China

ISBN: (纸本)9798350320404

As the complexity of software systems continues to increase, traditional monolithic software architectures will become difficult to scale and maintain. Microservices as an emerging software architecture it advocates decentralized management, service autonomy, and distinct module boundaries. These features of microservices make software systems easy to maintain, deploy, and modify. However, microservice identification is still not well addressed due to the lack of an effective approach. The existing work on microservice identification mainly starts from the system functionality perspective and does not take into account the actual business rules, which leads to microservice candidates not conforming to the concept of microservices. To address this challenge, we propose an automated approach to microservice identification that combines dynamic and static analysis and takes into account the actual business. Our proposed approach starts with a dynamic and static analysis of the monolithic system. Once the behavioral data of the system is collected, the behavioral data will be further processed according to our proposed guidelines. Then, the proposed approach calculates the degree of the correlation between classes in a monolithic system. Finally, we propose an improved clustering algorithm based on K-means to classify the classes in a monolithic system into different microservices. The proposed approach is validated by comparison with other approaches on open source projects. © 2022 IEEE.

关键词： K-means clustering

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：