检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yan, Yunlu Feng, Chun-Mei Ye, Mang Zuo, Wangmeng Li, Ping Goh, Rick Siow Mong Zhu, Lei Chen, C.L. Philip Guangzhou Nansha511400 China The Institute of High Performance Computing A*STAR Singapore138632 Singapore The Hubei Luojia Laboratory National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China The School of Computer Science and Technology Harbin Institute of Technology Harbin130407 China The Hong Kong University of Science and Technology Hong Kong The Department of Computing the School of Design The Hong Kong Polytechnic University Hong Kong The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Pazhou Lab Guangzhou510335 China

Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. However, the real-world non-IID data will lead to client drift which degrades the performance of FL. Interestingly, we find that the difference in logits between the local and global models increases as the model is continuously updated, thus seriously deteriorating FL performance. This is mainly due to catastrophic forgetting caused by data heterogeneity between clients. To alleviate this problem, we propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models. FedCSD does not simply transfer global knowledge to local clients, as an undertrained global model cannot provide reliable knowledge, i.e., class similarity information, and its wrong soft labels will mislead the optimization of local models. Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype. To enhance the quality of global logits, FedCSD adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them to mislead local optimization. Extensive experiments demonstrate the superiority of our method over the state-of-the-art federated learning approaches in various heterogeneous settings. The source code will be released. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

arXiv

引用

arXiv 2025年

作者： Chen, Qiguang Qin, Libo Liu, Jinhao Peng, Dengyun Guan, Jiannan Wang, Peng Hu, Mengkang Zhou, Yuhang Gao, Te Che, Wanxiang LARG China Research Center for Social Computing and Interactive Robotics China Harbin Institute of Technology China School of Computer Science and Engineering Central South University China The University of Hong Kong Hong Kong Fudan University China

Recent advancements in reasoning with large language models (RLLMs), such as OpenAI-O1 and DeepSeek-R1, have demonstrated their impressive capabilities in complex domains like mathematics and coding. A central factor in their success lies in the application of long chain-of-thought (Long CoT) characteristics, which enhance reasoning abilities and enable the solution of intricate problems. However, despite these developments, a comprehensive survey on Long CoT is still lacking, limiting our understanding of its distinctions from traditional short chain-of-thought (Short CoT) and complicating ongoing debates on issues like "overthinking" and "test-time scaling." This survey seeks to fill this gap by offering a unified perspective on Long CoT. (1) We first distinguish Long CoT from Short CoT and introduce a novel taxonomy to categorize current reasoning paradigms. (2) Next, we explore the key characteristics of Long CoT: deep reasoning, extensive exploration, and feasible reflection, which enable models to handle more complex tasks and produce more efficient, coherent outcomes compared to the shallower Short CoT. (3) We then investigate key phenomena such as the emergence of Long CoT with these characteristics, including overthinking, and test-time scaling, offering insights into how these processes manifest in practice. (4) Finally, we identify significant research gaps and highlight promising future directions, including the integration of multi-modal reasoning, efficiency improvements, and enhanced knowledge frameworks. By providing a structured overview, this survey aims to inspire future research and further the development of logical reasoning in artificial intelligence1 © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research Progress of Knowledge Graph and Attention Mechanism in Recommender Systems

Research Progress of Knowledge Graph and Attention Mechanism...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Mingzhu Huang Zhen Zhang Heng Qian Jie Liu Qiuyue Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shu Ju (Shandong) Intelligent Technology Co. Ltd. Jinan China Qingdao Electronics School Qingdao China Shandong Standard Institute of Emerging Technologies and Innovations Co. Ltd. Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

With the development of the Internet and the explosive expansion of information volume, it becomes arduous for users to make a choice in the face of overwhelming information. This makes the recommendation system an effective solution for the problem of information overload. Recommendation systems can acquire users' personalized preferences by comprehending their interactive behavior, thereby providing accurate recommendations. However, recommendation systems invariably encounter issues such as data sparsity and cold start. The introduction of auxiliary information can effectively alleviate these problems. Meanwhile, the employment of attention mechanisms can assist the system in more accurately understand user behavior and preference information, thus providing more precise personalized recommendations. In this paper, the research progress of knowledge graphs and attention mechanisms in recommendation systems is explored through top journals and several Chinese papers.

关键词： Attention mechanisms Accuracy Federated learning Employment Knowledge graphs Explosives Internet Recommender systems Faces

来源：评论

学校读者我要写书评

暂无评论

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

arXiv

引用

arXiv 2023年

作者： Qin, Libo Pan, Wenbo Chen, Qiguang Liao, Lizi Yu, Zhou Zhang, Yue Che, Wanxiang Li, Min School of Computer Science and Engineering Central South University China Harbin Institute of Technology China Research Center for Social Computing and Information Retrieval Cyprus Singapore Management University Singapore Department of Computer Science Columbia University United States School of Engineering Westlake University China

End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of large pre-trained models, has further led to significant progress in EToD research in recent years. In this paper, we present a thorough review and provide a unified perspective to summarize existing approaches as well as recent trends to advance the development of EToD research. The contributions of this paper can be summarized: (1) First survey: to our knowledge, we take the first step to present a thorough survey of this research field;(2) New taxonomy: we first introduce a unified perspective for EToD, including (i) Modularly EToD and (ii) Fully EToD;(3) New Frontiers: we discuss some potential frontier areas as well as the corresponding challenges, hoping to spur breakthrough research in EToD field;(4) Abundant resources: we build a public website1, where EToD researchers could directly access the recent progress. We hope this work can serve as a thorough reference for the EToD research community. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Lane marking detection algorithm based on high-precision map and multisensor fusion

Lane marking detection algorithm based on high-precision map...

引用

作者： Yao, Haichang Chen, Chen Liu, Shangdong Li, Kui Ji, Yimu Huang, Guangyan Wang, Ruchuan School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer and Software Nanjing Institute of Industry Technology Nanjing China Industrial Software Engineering Technology Research and Development Center of Jiangsu Education Department Nanjing Institute of Industry Technology Nanjing China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing China School of Information Technology Deakin University Melbourne Australia

In case of sharp road illumination changes, bad weather such as rain, snow or fog, wear or missing of the lane marking, the reflective water stain on the road surface, the shadow obstruction of the tree, and mixed lane markings and other signs, missing detection or wrong detection will occur for the traditional lane marking detection algorithm. In this manuscript, a lane marking detection algorithm based on high-precision map and multisensor fusion is proposed. The basic principle of the algorithm is to use the centimeter-level high-precision positioning combined with high-precision map data to complete the detection of lane markings. In the process of generating high-precision maps or in the uncovered areas of high-precision maps, LIDAR (LIght Detection And Ranging) is used to estimate the curvature of the road to assist in lane marking detection. The experimental results show that the algorithm has lower false detection rate in case of bad road conditions, and the algorithm is robust. © 2020 John Wiley & Sons, Ltd.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Multi-Turn Jailbreaking Large Language Models via Attention Shifting 39

Multi-Turn Jailbreaking Large Language Models via Attention ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Xiaohu Mo, Fan Wen, Ming Gu, Tu Zheng, Huadi Jin, Hai Shi, Jie China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab School of Computer Science and Technology HUST China JinYinHu Laboratory China Huawei International China

ISBN: (纸本)157735897X

Large Language Models (LLMs) have achieved significant performance in various natural language processing tasks but also pose safety and ethical threats, thus requiring red teaming and alignment processes to bolster their safety. To effectively exploit these aligned LLMs, recent studies have introduced jailbreak attacks based on multi-turn dialogues. These attacks aim to prompt LLMs to generate harmful or biased content by guiding them through contextual content. However, the underlying reasons for the effectiveness of multi-turn jailbreaks remain unclear. Existing attacks often focus on optimizing queries and escalating toxicity to construct dialogues, lacking a thorough analysis of the inherent vulnerabilities of LLMs. In this paper, we first conduct an in-depth analysis of the differences between single-turn and multi-turn jailbreaks and find that successful multi-turn jailbreaks can effectively disperse the attention of LLMs on keywords associated with harmful behaviors, especially in historical responses. Based on this, we propose ASJA, a new multi-turn jailbreak approach by shifting the attention of LLMs, specifically by iteratively fabricating the dialogue history through a genetic algorithm to induce LLMs to generate harmful content. Extensive experiments on three LLMs and two datasets show that our approach surpasses existing approaches in jailbreak effectiveness, the stealth of jailbreak prompts, and attack efficiency. Our work emphasizes the importance of enhancing the robustness of LLMs’ attention mechanism in multi-turn dialogue scenarios for a better defense strategy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Memory Architecture Supporting Fine-Grained Data Migration

SSRN

引用

SSRN 2022年

作者： Chi, Ye Yue, Jianhui Liao, Xiaofei Liu, Haikun Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Computer Science Michigan Technological University HoughtonMI United States

We propose Mocha, a non-hierarchical caching architecture that organizes DRAM and NVM in a flat address space physically, but manages DRAM/NVM in a cache/memory hierarchy in this paper. Since the commercial NVM device-Intel Optane DC Persist Memory Modules (DCPMM) actually access the physical media at a granularity of 256 bytes (an Optane block), we manage the DRAM cache at the 256-byte size to adapt to this device feature of Optane. This design not only enables fine-grained data migration and management for the DRAM cache, but also avoids write amplification for Optane DCPMM. We also create a the \textit{ Indirect Address Cache} (IAC) in \textit{Hybrid Memory Controller}(HMC) and propose a reverse address mapping table in the DRAM to speed up address translation and cache replacement. Besides, we exploit an utility-based caching mechanism to filter cold blocks in the NVM, and further improve DRAM cache effectiveness. We implement Mocha in an architecture simulator. Experimental results indicate that MOCHA can improve performance of applications by 8.2\% on average (up to 24.6\%), provide 6.9\% reduction in average energy consumption and 25.9\% reduction in average data migration traffic, compared to the most advanced hybrid memory architecture-HSCC. © 2022, The Authors. All rights reserved.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

Prototypical Residual Networks for Anomaly Detection and Localization

Prototypical Residual Networks for Anomaly Detection and Loc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hui Zhang Zuxuan Wu Zheng Wang Zhineng Chen Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Zhejiang University of Technology

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, anomalies are typically subtle, hard to discern, and of various appearance, making it difficult to detect anomalies and let alone locate anomalous regions. To address these issues, we propose a framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. PRN mainly consists of two parts: multi-scale prototypes that explicitly represent the residual features of anomalies to normal patterns; a multisize self-attention mechanism that enables variable-sized anomalous feature learning. Besides, we present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies. Extensive experiments on the challenging and widely used MVTec AD benchmark show that PRN outperforms current state-of-the-art unsupervised and supervised methods. We further report SOTA results on three additional datasets to demonstrate the effectiveness and generalizability of PRN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variational Bayes for Federated Continual Learning

arXiv

引用

arXiv 2024年

作者： Yao, Dezhong Li, Sanmu Dai, Yutong Xu, Zhiqiang Hu, Shengshan Zhao, Peilin Sun, Lichao The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Lehigh University PA18015 United States Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Tencent AI Lab. Shenzhen China

Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time. The constraints of storage limitations and privacy concerns confine local models to exclusively access the present data within each learning cycle. Consequently, this restriction induces performance degradation in model training on previous data, termed "catastrophic forgetting". However, existing FCL approaches need to identify or know changes in data distribution, which is difficult in the real world. To release these limitations, this paper directs attention to a broader continuous framework. Within this framework, we introduce Federated Bayesian Neural Network (FedBNN), a versatile and efficacious framework employing a variational Bayesian neural network across all clients. Our method continually integrates knowledge from local and historical data distributions into a single model, adeptly learning from new data distributions while retaining performance on historical distributions. We rigorously evaluate FedBNN’s performance against prevalent methods in federated learning and continual learning using various metrics. Experimental analyses across diverse datasets demonstrate that FedBNN achieves state-of-the-art results in mitigating forgetting. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs

arXiv

引用

arXiv 2024年

作者： Gui, Yi Li, Zhen Wan, Yao Shi, Yemin Zhang, Hongyu Su, Yi Chen, Bohua Chen, Dongping Wu, Siyuan Zhou, Xing Jiang, Wenbin Jin, Hai Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Peking University Beijing China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. The code and dataset are publicly available at our project homepage: https://***. Copyright © 2024, The Authors. All rights reserved.

关键词： Web Design

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：