检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Luo, Wenqiang Keung, Jacky Wai Yang, Boyang Klein, Jacques Bissyandé, Tegawendé F. Tian, Haoye Le, Bach Department of Computer Science City University of Hong Kong China Jisuan Institute of Technology Beijing JudaoYouda Network Technology Co. Ltd China SnT University of Luxembourg Luxembourg School of Computing and Information Systems University of Melbourne Australia

Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainstream programming languages like Java and Python, neglecting less prevalent but emerging languages such as Rust due to expensive training resources, limited datasets, and insufficient community support. This narrow focus creates a significant gap in repair capabilities across the programming language spectrum, where the full potential of LLMs for comprehensive multilingual program repair remains largely unexplored. To address this limitation, we introduce a novel cross-language program repair approach LANTERN that leverages LLMs’ differential proficiency across languages through a multi-agent iterative repair paradigm. Our technique strategically translates defective code from languages where LLMs exhibit weaker repair capabilities to languages where they demonstrate stronger performance, without requiring additional training. A key innovation of our approach is an LLM-based decision-making system that dynamically selects optimal target languages based on bug characteristics and continuously incorporates feedback from previous repair attempts. We evaluate our method on xCodeEval, a comprehensive multilingual benchmark comprising 5,068 bugs across 11 programming languages. Results demonstrate significant enhancement in repair effectiveness, particularly for underrepresented languages, with Rust showing a 22.09% improvement in Pass@10 metrics. Our research provides the first empirical evidence that cross-language translation significantly expands the repair capabilities of LLMs and effectively bridges the performance gap between programming languages with different levels of popularity, opening new avenues for truly language-agnostic automated program repair. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

arXiv

引用

arXiv 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan The Beijing Key Laboratory of Network System Architecture and Convergence The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing China Singapore The Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Computer Science North Carolina State University RaleighNC27695 United States The Beijing Key Laboratory of Network System Architecture and Convergence China The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing100876 China

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

DFMC:Feature-Driven Data-Free Knowledge Distillation

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Zhang, Zherui Xu, Rongtao Wang, Changwei Xu, Wenhao Chen, Shunpeng Xu, Shibiao Xu, Guangyuan Guo, Li Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Qilu University of Technology Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250316 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from teacher networks without access to the real dataset. However, generator-based DFKD methods often suffer from insufficient diversity or low-confidence in synthetic images, negatively impacting student network performance. This paper introduces DFMC, a generative feature-driven framework to mitigate the inherent limitations of DFKD. We propose exploiting semantic description between generative feature domains to guide augmentation strategies, avoiding random abstract inputs caused by inconsistent semantic quality. Then, by applying noise to the generative features, we produce contrastive learning pairs indirectly, limiting the sampling range of the feature domain to encourage the student network to learn domain-invariant features. Finally, we guide the student network to deeply mimic the teacher’s layer-wise implicit classification behavior for the augmented synthetic images. Extensive experiments across various datasets and downstream tasks demonstrate the effectiveness of DFMC, achieving significant improvements while preventing student networks from overfitting to semantic ambiguous images. © 1991-2012 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Classifying stances of interaction posts in social media debate sites 11th

Classifying stances of interaction posts in social media deb...

引用

11th International Conference on Intelligent computing, ICIC 2015

作者： Rong, Xiaosong Wang, Zhuo Wang, Ziqi Zhang, Ming Institute of Network Computing and Information Systems School of Electronics Engineering and Computer Science Peking University Beijing100871 China

ISBN: (纸本)9783319221854

Social media debate sites provide a rich collection of public opinions on various controversial issues. In an online debate, participants express their stances by replying directly to the main topic or indirectly to other participants. We observe that the majority of the posts in online debates are interaction posts. In this paper, we propose a new method for the task of stance classification of interaction posts in online debates. We mine the historical activities and textual content of posts to learn the relationships between participants in online debates. Then we build the interaction graph and develop a greedy algorithm to classify participants by stance. Empirical evaluation shows that our method performs better than the baseline methods. © Springer International Publishing Switzerland 2015.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Mining learners' disorientation in Web-based learning

Mining learners' disorientation in Web-based learning

引用

18th International Conference on Computers in Education, ICCE 2010

作者： Shih, Yu-Cheng Hsu, Yung-Chi Chen, Sherry Y. Graduate Institute of Network Learning Technology National Central University Taiwan Department of Information Systems and Computing Brunel University United Kingdom

ISBN: (纸本)9789834251246

Web-based learning systems provide flexible ways for learners to develop their own learning strategies. However, some learners may experience more disorientation problems when they need to decide the learning strategies by themselves. In other words, not all of learners are suitable to use the Web-based learning systems. Therefore, it is necessary to investigate how learners' individual differences influence their disorientation problems. To this end, this study addresses this issue. Unlike other previous studies, we will not only examine how learners' individual differences influence their disorientation but also investigate how the learners' disorientation influences their learning performance. The other novelty of this study is the fact that we use a data mining approach to conduct data analyses. The results indicate that learners' computer experience is a major factor to influence their disorientation. Moreover, their disorientation may also influence their learning performance. The results are useful for developing Web-based learning systems to reduce learners' disorientation.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Attribute-Based Signature with Policy-and-Endorsement Mechanism

引用

Journal of Computer Science & Technology 2010年第6期25卷 1293-1304页

作者：王怀习朱岩冯荣权 Stephen S.Yau LMAM School of Mathematical SciencesPeking University Electronic Engineering Institute Institute of Computer Science and Technology Peking University Key Laboratory of Network and Software Security Assurance (Peking University) Ministry of Education Information Assurance Center and School of Computing Informatics and Decision Systems Engineering Arizona State University

In this paper a new signature scheme,called Policy-Endorsing Attribute-Based Signature,is developed to correspond with the existing Ciphertext-Policy Attribute-Based *** signature provides a policy-and-endorsement *** this mechanism a single user,whose attributes satisfy the predicate,endorses the *** signature allows the signer to announce his endorsement using an access policy without having to reveal the identity of the *** security of this signature,selfless anonymity and existential unforgeability,is based on the Strong Diffie-Hellman assumption and the Decision Linear assumption in bilinear map groups.

关键词： cryptography fine-grained access control attribute-based signature policy-and-endorsement selfless anonymity existential unforgeability

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision

arXiv

引用

arXiv 2025年

作者： Han, Xiaofeng Chen, Shunpeng Fu, Zenghuang Feng, Zhe Fan, Lue An, Dong Wang, Changwei Guo, Li Meng, Weiliang Zhang, Xiaopeng Xu, Rongtao Xu, Shibiao The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center China

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We systematically review the applications of multimodal fusion in key robotic vision tasks, including semantic scene understanding, simultaneous localization and mapping (SLAM), 3D object detection, navigation and localization, and robot manipulation. We compare VLMs based on large language models (LLMs) with traditional multimodal fusion methods, analyzing their advantages, limitations, and synergies. Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Furthermore, we identify critical research challenges such as cross-modal alignment, efficient fusion strategies, real-time deployment, and domain adaptation, and propose future research directions, including self-supervised learning for robust multimodal representations, transformer-based fusion architectures, and scalable multimodal frameworks. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://***/Xiaofeng-Han-Res/MF-RV. Copyright © 2025, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Influence of prior knowledge and cognitive styles in Adaptive Hypermedia Learning systems

Influence of prior knowledge and cognitive styles in Adaptiv...

引用

19th International Conference on Computers in Education, ICCE 2011

作者： Mampadi, Freddy Ghinea, Gheorghita Huang, Pei-Ren Chen, Sherry Y. Department of Information Systems and Computing Brunel University United Kingdom Graduate Institute of Network Learning Technology National Central University Taiwan

ISBN: (纸本)9786161201883

Most Adaptive Hypermedia Learning systems (AHLSs) tailor presentation content and navigational support based on prior knowledge or cognitive styles of students separately. There is, however, a need to explore how the two individual difference characteristics could be combined in adaptive hypermedia learning systems in order to maximize learning and comprehension of educational materials. To this end, the study presented in this paper developed two adaptive hypermedia learning systems, one tailored to students' prior knowledge, with the other tailored to their cognitive styles, with emphasis on Pask's Holist-Serialist dimension. Findings indicate that, in general, adapting to either prior knowledge or cognitive styles improves learning performance.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

On the cascading spectrum contention problem in self-coexistence of cognitive radio networks

On the cascading spectrum contention problem in self-coexist...

引用

1st ACM Workshop on Cognitive Radio Architectures for Broadband, CRAB 2013

作者： Chen, Lin Bian, Kaigui Yan, Wei Li, Xiaoming Institute of Network Computing and Information Systems School of EECS Peking University Beijing 100871 China University Paris-Sud 91405 Orsay France

ISBN: (纸本)9781450323680

In cognitive radio (CR) networks, the coexistence between neighboring secondary networks is referred to as self coexistence. As prescribed in IEEE 802.22, a self-coexistence protocol enables a CR network in need of more spectrum resources to acquire spectrum (channels) from neighboring CR networks via a distributed inter-network spectrum contention process. A network that forfeits part of its spectrum in a spectrum contention process may later become short of spectrum, and in turn, it initiates a cascading spectrum contention process to acquire more spectrum resources. As a result, a local spectrum contention may trigger a series of successive contention instances that proliferate over the whole network, which may waste the network resources. In this paper, we systematically study the cascading spectrum contention problem using a percolation-based model in the context of CR networks. We show that cascading spectrum contentions under existing spectrum contention resolution rules is equivalent to a site percolation process that can readily lead to a network-wide cascade. To address such a problem, we identify the critical conditions for determining the occurrence of cascading spectrum contentions, and propose a biased spectrum contention protocol that intentionally lowers the probability that a starving network can trigger successive spectrum contentions. We show that the proposed solution can effectively restrict the spatial cascading impact of contentions. Copyright 2013 ACM.

关键词： Cognitive radio

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：