检索结果-内蒙古大学图书馆

Frontiers of collaborative intelligence systems

Journal of Information and Intelligence 2024年第1期2卷 14-27页

作者： Maoguo Gong Yajing He Hao Li Yue Wu Mingyang Zhang Shanfeng Wang Tianshi Luo School of Electronic Engineering Key Laboratory of Collaborative Intelligence SystemsMinistry of EducationXidian UniversityXi'an 710071China School of Computer Science and Technology Key Laboratory of Collaborative Intelligence SystemsMinistry of EducationXidian UniversityXi'an 710071China School of Cyber Engineering Key Laboratory of Collaborative Intelligence SystemsMinistry of EducationXidian UniversityXi'an 710071China

The development of information technology has propelled technological reform in artificial intelligence(AI).To address the needs of diversified and complex applications,AI has been increasingly trending towards intelligent,collaborative,and systematized development across different levels and *** on intelligent,collaborative and systematized AI can be divided into three levels:micro,meso,and ***,the micro-level collaboration is illustrated through the introduction of swarm intelligence collaborative methods related to individuals collaboration and decision variables ***,the meso-level collaboration is discussed in terms of multi-task collaboration and multi-party ***,the macro-level collaboration is primarily in the context of intelligent collaborative systems,such as terrestrial-satellite collaboration,space-air-ground collaboration,space-air-ground-air collaboration,vehicle-road-cloud collaboration and end-edge-cloud ***,this paper provides prospects on the future development of relevant fields from the perspectives of the micro,meso,and macro levels.

关键词： Artificial intelligence collaboration mechanism Micro,meso and macro collaboration Artificial intelligence mega application

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: AFS: Improving Accuracy of Quantized Mamba via Aggressive Forgetting Strategy

Late Breaking Results: AFS: Improving Accuracy of Quantized ...

引用

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Liu, Zhouquan Huang, Libo Yang, Ling Chen, Gang Liu, Wei Lai, Mingche Wang, Yongwen College of Computer Science and Technology National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9783982674100

Mamba overcomes the quadratic complexity problem inherent in Transformer models while maintaining comparable contextual modeling capabilities. However, Mamba-based foundation models encounter challenges in achieving efficient inference on resource-constrained devices, primarily due to their considerable size. Model compression techniques, such as linear quantization, offer a viable solution to this problem. Nevertheless, the introduction of significant outliers during Mamba's past-state forgetting process can lead to a notable decrease in accuracy when employing linear quantization. To overcome these challenges, this paper introduces the Aggressive Forgetting Strategy (AFS), an innovative and efficient algorithm designed to mitigate the quantization issues caused by outliers in the state forgetting mechanism. AFS incorporates a computation-free approach for handling outliers, facilitating both efficient and accurate linear quantization for Mamba, which is essential for applications in resource-constrained scenarios. By leveraging the AFS strategy, Mamba can perform more efficient inference, while significantly improving the accuracy by up to 21.5× compared to conventional methods. © 2025 EDAA.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matching 24

BinaryAI: Binary Software Composition Analysis via Intellige...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Jiang, Ling An, Junwen Huang, Huihui Tang, Qiyi Nie, Sen Wu, Shi Zhang, Yuqun Southern University of Science and Technology Shenzhen China Tencent Security Keen Lab Shanghai China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Southern University of Science and Technol-ogy Department of Computer Science and Engineering Shenzhen China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation China

ISBN: (纸本)9798400702174

While third-party libraries (TPLs) are extensively reused to enhance productivity during software development, they can also introduce potential security risks such as vulnerability propagation. Software composition analysis (SCA), proposed to identify reused TPLs for reducing such risks, has become an essential procedure within modern DevSecOps. As one of the mainstream SCA techniques, binary-to-source SCA identifies the third-party source projects contained in binary files via binary source code matching, which is a major challenge in reverse engineering since binary and source code exhibit substantial disparities after compilation. The existing binary-to-source SCA techniques leverage basic syntactic features that suffer from redundancy and lack robustness in the large-scale TPL dataset, leading to inevitable false positives and compromised recall. To mitigate these limitations, we introduce BinaryAI, a novel binary-to-source SCA technique with two-phase binary source code matching to capture both syntactic and semantic code features. First, BinaryAI trains a transformer-based model to produce function-level embeddings and obtain similar source functions for each binary function accordingly. Then by applying the link-time locality to facilitate function matching, BinaryAI detects the reused TPLs based on the ratio of matched source functions. Our experimental results demonstrate the superior performance of BinaryAI in terms of binary source code matching and the downstream SCA task. Specifically, our embedding model outperforms the state-of-the-art model CodeCMR, i.e., achieving 22.54% recall@l and 0.34 MRR compared with 10.75% and 0.17 respectively. Additionally, BinaryAI outperforms all existing binary-to-source SCA tools in TPL detection, increasing the precision from 73.36% to 85.84% and recall from 59.81% to 64.98% compared with the well-recognized commercial SCA product Black Duck. E-https://*** © 2024 ACM.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

CMD: A Cache-assisted GPU Memory Deduplication Architecture

arXiv

引用

arXiv 2024年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing The Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck, and we divided these accesses into three types: (1) Write, (2) Data-Read, and (3) Read-Only. Besides, We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the inter-dup and inter-dup lines. As for the inter-dup detection, we reduce the extra read requests caused by the traditional read-verify hash process. Besides, we design several techniques to manage duplicate blocks. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 37.79%. Besides, CMD can improve the performance of memory-intensive workloads by 50.18%. © 2024, CC BY-NC-ND.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Forecasting-Aided Graphical Learning for Robust State Estimation of Distribution System 1

引用

8th Purple Mountain Forum on Smart Grid Protection and Control, PMF 2023

作者： Di, Cao Zhao, Junbo Hu, Jiaxiang Huang, Yuehui Huang, Qi Chen, Zhe Hu, Weihao University of Electronic Science and Technology of China Chengdu China Department of Electrical and Computer Engineering University of Connecticut StorrsCT06269 United States State Key Laboratory of Operation and Control of Renewable Energy and Storage Systems China Electric Power Research Institute Beijing China Department of Energy Technology Aalborg University Pontoppidanstraede 111 Aalborg Denmark

ISBN: (数字)9789819992515

ISBN: (纸本)9789819992508

The forecasting of of pseudo-measurements play an important role in distribution system state estimation (DSSE). This paper proposes robust DSSE method based on forecasting-aided graphical learning method. The nodal power consumption models are first built to produce pseudo-measurements based on deep neural network. Then, the pseudo-measurements and real-time measurements are represented as a graph according to the topology of the distribution network, which are further processed by a graph attention network to capture the mapping relationship between the graphical measurements and the state variables based on the error modeling of pseudo-measurements. The robustness against anomalous measurements is achieved through the embedding of structural information of DN. The modeling of pseudo-measurements further enhance its robustness by guiding the formulation of edge weights of the graph neural network. Comparative tests are carried out on a IEEE 119-node system to demonstrate the effectiveness and robustness of the proposed method. © 2024, State Grid Electric Power.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks 39

CtrlAvatar: Controllable Avatars Generation via Disentangled...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Song, Wenfeng Ding, Yang Hou, Fei Li, Shuai Hao, Aimin Hou, Xia College of Computer Science Beijing Information Science and Technology University China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Zhongguancun Laboratory China

ISBN: (纸本)157735897X

As virtual experiences grow in popularity, the demand for realistic, personalized, and animatable human avatars increases. Traditional methods, relying on fixed templates, often produce costly avatars that lack expressiveness and realism. To overcome these challenges, we introduce Controllable Avatars generation via disentangled invertible networks (CtrlAvatar), a real-time framework for generating lifelike and customizable avatars. CtrlAvatar uses disentangled invertible networks to separate the deformation process into implicit body geometry and explicit texture components. This approach eliminates the need for repeated occupancy reconstruction, enabling detailed and coherent animations. The body geometry component ensures anatomical accuracy, while the texture component allows for complex, artifact-free clothing customization. This architecture ensures smooth integration between body movements and surface details. By optimizing transformations with position-varying offsets from the avatar’s initial Linear Blend Skinning vertices, CtrlAvatar achieves flexible, natural deformations that adapt to various scenarios. Extensive experiments show that CtrlAvatar outperforms other methods in quality, diversity, controllability, and cost-efficiency, marking a significant advancement in avatar generation. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

A Positioning and Navigation System for Railway Technical Station Operators 4

A Positioning and Navigation System for Railway Technical St...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Yang, Fan Wang, Zhixue Xiong, Gang Hu, Xiangyu Xu, Kejie Chen, Shichao Shandong Jiaotong University State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Rail Transportation Jinan China Shandong Jiaotong University School of Rail Transportation Jinan China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Beijing Technol. and Bus. Univ. State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Computer and Artificial Intelligence Beijing China China Mobile Communication Group Sichuan Co. Ltd Chengdu China Chinese Academy of Sciences Beijing Huairou Academy of Parallel Sensing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China

ISBN: (纸本)9798350349252

As an important node in the dismantling and grouping of freight trains, the operational tasks of the railway technical station are increasingly busy. Various business activities involve a large number of field personnel, and ensuring the personal safety and operational efficiency of these personnel is one of these issues that railway operations need to *** ensure the operational safety and standardization at the railway technical station, high-precision positioning system for the personnel is required. However, typical operational scenarios at railway technical stations often involve problems such as the carriage obstruction and the electromagnetic interference. Only rely on GNSS for positioning is often insufficient to meet practical requirements. Addressing the need of the high-precision positioning for the operational personnel at railway technical stations, this paper constructs a integrated navigation system based on RTK and IMU. It utilizes a Discrete Error State Kalman Filtering algorithm to fuse the solution data from RTK and IMU, thereby obtaining high-precision pedestrian positioning data. Compared to relying solely on GNSS positioning system, the integrated navigation system significantly improves its resistance to the interference and positioning accuracy. Experimental results demonstrate that this positioning system can achieve centimeter-level positioning in obstructed scenarios typical of railway technical stations, meeting the positioning requirements of the operational personnel at railway technical station work sites. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

RTV Silicone Rubber Coatings for Outdoor Insulators: A Concise Review of Some Factors Affecting their Behavior and Some Comments

引用

Journal of Engineering Science and technology Review 2021年第1期14卷 163-169页

作者： Sarathi, R. Danikas, M.G. Indian Institute of Technology Madras Department of Electrical Engineering High Voltage Laboratory Chennai India Democritus University of Thrace Department of Electrical and Computer Engineering Power Systems Laboratory Xanthi67100 Greece

Traditional outdoor insulators are made of glass and porcelain. However, although such insulators have been used for many decades, they present some drawbacks. Glass and porcelain insulators seem to be more prone to surface discharges and flashover when they age and water droplets are more likely to spread on their surface, causing thus dry zones and consequently conditions for surface discharging and flashover. Room Temperature Vulcanized (RTV) coatings spayed on the aforementioned traditional insulators seem to remedy such problems because such coatings increase the hydrophobicity. In this paper, a short review on RTV coatings is given together with some thoughts and comments regarding the so-called early stage of aging. © 2021 School of Science, IHU. All rights reserved.

关键词： Contact angle

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: AFS: Improving Accuracy of Quantized Mamba via Aggressive Forgetting Strategy

Late Breaking Results: AFS: Improving Accuracy of Quantized ...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Zhouquan Liu Libo Huang Ling Yang Gang Chen Wei Liu Mingche Lai Yongwen Wang College of Computer Science and Technology National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

关键词： Performance evaluation Quantization (signal) Accuracy Foundation models Logic gates Transformers Inference algorithms Complexity theory Standards Context modeling

来源：评论

学校读者我要写书评

暂无评论

Fast CU Partition for VVC Using Texture Complexity Classification Convolutional Neural Network

引用

computers, Materials & Continua 2022年第11期73卷 3545-3556页

作者： Yue Zhang Pengyu Liu Xiaowei Jia Shanji Chen Tianyu Liu Chang Liu The Information Department Beijing University of TechnologyBeijing100124China School of Physics and Electronic Information Engineering Qinghai Minzu UniversityXining810000China Advanced Information Network Beijing Laboratory Beijing100124China Computational Intelligence and Intelligent Systems Beijing Key Laboratory Beijing100124China Department of Computer Science University of PittsburghPittsburgh15260USA

Versatile video coding(H.266/VVC),which was newly released by the Joint Video Exploration Team(JVET),introduces quad-tree plus multitype tree(QTMT)partition structure on the basis of quad-tree(QT)partition structure in High Efficiency Video Coding(H.265/HEVC).More complicated coding unit(CU)partitioning processes in H.266/VVC significantly improve video compression efficiency,but greatly increase the computational complexity *** ultra-high encoding complexity has obstructed its real-time *** order to solve this problem,a CU partition algorithm using convolutional neural network(CNN)is proposed in this paper to speed up the H.266/VVC CU partition ***,64×64 CU is divided into smooth texture CU,mildly complex texture CU and complex texture CU according to the CU texture ***,CU texture complexity classification convolutional neural network(CUTCC-CNN)is proposed to classify ***,according to the classification results,the encoder is guided to skip different RDO search *** optimal CU partition results will be *** results show that the proposed method reduces the average coding time by 32.2%with only 0.55%BD-BR loss compared with VTM 10.2.

关键词： Versatile video coding(VVC) coding unit partition convolutional neural network(CNN)

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：