检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Liu, Pusheng Wu, Lianwei Wang, Linyong Guo, Sensen Liu, Yang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China Research & Development Institute of Northwestern Polytechnical University Shenzhen China Chongqing Science & Technology Innovation Center of Northwestern Polytechnical University China State Key Laboratory of Integrated Service Networks Xidian University China School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University China

ISBN: (纸本)9782493814104

Recently, the autoregressive framework based on large language models (LLMs) has achieved excellent performance in controlling the generated text to adhere to the required style. These methods guide LLMs through prompt learning to generate target text in an autoregressive manner. However, this manner possesses lower controllability and suffers from the challenge of accumulating errors, where early prediction inaccuracies might influence subsequent word generation. Furthermore, existing prompt-based methods overlook specific region editing, resulting in a deficiency of localized control over input text. To overcome these challenges, we propose a novel three-stage prompt-based approach for specific region editing. To alleviate the issue of accumulating errors, we transform the text style transfer task into a text infilling task, guiding the LLMs to modify only a small portion of text within the editing region to achieve style transfer, thus reducing the number of autoregressive iterations. To achieve an effective specific editing region, we adopt both prompt-based and word frequency-based strategies for region selection, subsequently employing a discriminator to validate the efficacy of the selected region. Experiments conducted on several publicly competitive datasets for text style transfer task confirm that our proposed approach achieves state-of-the-art performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Highly integrated reconfigurable radiofrequency filter based on microcomb and a silicon photonic processor

Highly integrated reconfigurable radiofrequency filter based...

引用

CLEO: Science and Innovations, S and I 2022

作者： Tao, Yuansheng Chang, Lin Shen, Bitao Shu, Haowen Xie, Weiqiang Jin, Ming Tao, Zihan Bai, Bowen Yu, Shaohua Wang, Xingjun Bowers, John E. State Key Laboratory of Advanced Optical Communications System and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Peng Cheng Laboratory Shenzhen518055 China Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China

We demonstrate a novel chip-scale reconfigurable radiofrequency filter by using AlGaAs-on-insulator microcomb and silicon photonics in combination, simultaneously bypassing the employment of bulky pulse shaper and lon... 详细信息

ISBN: (纸本)9781557528209

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Enhanced Chip-on-board Hybrid-Packaged Photonic-Electrical Silicon Transceiver for High-speed Optical Interconnects

Deep Neural Network Enhanced Chip-on-board Hybrid-Packaged P...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Qin, Jun Yang, Qipeng Han, Changhao Zhou, Yan Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Liu, Siming Li, Yueqin Sun, Jian Min, Miao Hu, Weiwei He, Zhixue Wang, Lei Yu, Shaohua Shu, Haowen Wang, Xingjun Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing100192 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China Peng Cheng Laboratory Shenzhen518055 China State Key Laboratory of Information Photonics and Optical Communications BUPT Beijing100876 China

We explore implementing a multilevel deep neural network to enhance the performance of a 4-channel photonic-electrical hybrid-packaged silicon transceiver. Stable transmission and reception of 150 Gbps/λ PAM4 signals... 详细信息

关键词： Optical interconnects

来源：评论

学校读者我要写书评

暂无评论

Throughput Analysis of SIC-Based Two-Device Slotted ALOHA with Feedback Over Nakagami-$m$ Fading Channels

Throughput Analysis of SIC-Based Two-Device Slotted ALOHA wi...

引用

International Symposium on Information Theory and Its Applications, ISITA

作者： Daiki Fukui Yuhei Takahashi Guanghui Song Tomotaka Kimura Zilong Liu Jun Cheng Department of Intelligent Information Engineering and Sciences Doshisha University Kyoto Japan The State Key Laboratory of Integrated Services Networks Xidian University Xi'an China School of Computer Science and Electronic Engineering University of Essex Colchester UK

ISBN: (数字)9784885523519

ISBN: (纸本)9798331533335

Throughput analysis for successive interference cancellation-based two-device slotted ALOHA with feedback is studied over Nakagami-m fading channels. Explicit expressions for the state transition probabilities are derived for a Markov process, thus facilitating the computation of the throughput. Through optimization of the transmission probability, it is shown that the maximum throughput is achieved for a given code rate.

关键词： Fading channels Nakagami distribution Codes Interference cancellation Markov processes Throughput Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Enhanced Chip-on-board Hybrid-Packaged Photonic-Electrical Silicon Transceiver for High-speed Optical Interconnects

Deep Neural Network Enhanced Chip-on-board Hybrid-Packaged P...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

ISBN: (纸本)9781957171395

关键词： Optical interconnects

来源：评论

学校读者我要写书评

暂无评论

Practical Volume-Hiding Encrypted Multi-Maps with Optimal Overhead and Beyond 22

Practical Volume-Hiding Encrypted Multi-Maps with Optimal Ov...

引用

28th ACM SIGSAC Conference on computer and Communications Security, CCS 2022

作者： Wang, Jianfeng Sun, Shi-Feng Li, Tianci Qi, Saiyu Chen, Xiaofeng School of Cyber Engineering Xidian University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China School of Computer Science and Technology Xi'an Jiao Tong University China State Key Laboratory of Integrated Service Networks Xidian University China

ISBN: (纸本)9781450394505

Encrypted multi-map (EMM), as a special case of structured encryption, has attracted extensive attention recently. However, most of EMM constructions reveal the real volumes of queried keys, which can be leveraged to launch leakage-abuse attacks, as demonstrated by Kellaris et al. in CCS 2016 and Kornaropoulos et al. in S&P 2021. In this paper, we propose a practical non-lossy volume-hiding EMM scheme, XorMM, that can achieve optimal query communication complexity with minimal storage cost. Specifically, compared to the state-of-the-art dprfMM (Patel et al. CCS 2019), the client in our scheme receives only ĝ.,"matching results while not suffering from data loss, where ĝ.,"is the maximum volume of all keys. In addition, the storage cost of XorMM is approximately 1.23n, where n is the total number of key/value pairs. In contrast, the query communication and storage complexity of dprfMM is 2ĝ.,"and 2(1+α)n respectively, where 0 © 2022 ACM.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge

FlowMur: A Stealthy and Practical Audio Backdoor Attack with...

引用

IEEE Symposium on Security and Privacy

作者： Jiahe Lan Jie Wang Baochen Yan Zheng Yan Elisa Bertino The State Key Laboratory on Integrated Services Networks School of Cyber Engineering Xidian University China Hangzhou Institute of Technology Xidian University China Department of Computer Science Purdue University USA

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Speech recognition systems driven by Deep Neural networks (DNNs) have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns on their security, particularly regarding backdoor attacks. A backdoor attack inserts one or more hidden backdoors into a DNN model during its training process, such that it does not affect the model’s performance on benign inputs, but forces the model to produce an adversary-desired output if a specific trigger is present in the model input. Despite the initial success of current audio backdoor attacks, they suffer from the following limitations: (i) Most of them require sufficient knowledge, which limits their widespread adoption. (ii) They are not stealthy enough, thus easy to be detected by humans. (iii) Most of them cannot attack live speech, reducing their practicality. To address these problems, in this paper, we propose FlowMur, a stealthy and practical audio backdoor attack that can be launched with limited knowledge. FlowMur constructs an auxiliary dataset and a surrogate model to augment adversary knowledge. To achieve dynamicity, it formulates trigger generation as an optimization problem and optimizes the trigger over different attachment positions. To enhance stealthiness, we propose an adaptive data poisoning method according to Signal-to-Noise Ratio (SNR). Furthermore, ambient noise is incorporated into the process of trigger generation and data poisoning to make FlowMur robust to ambient noise and improve its practicality. Extensive experiments conducted on two datasets demonstrate that FlowMur achieves high attack performance in both digital and physical settings while remaining resilient to state-of- the-art defenses. In particular, a human study confirms that triggers generated by FlowMur are not easily detected by participants. The source code of FlowMur is publicly available at https:/

关键词： Training Adaptation models Source coding Speech recognition Artificial neural networks Speech enhancement Security

来源：评论

学校读者我要写书评

暂无评论

Multi Criteria Decision Making Technique for Evaluation and Selection performance Large Scale Data of Composite Materials

Multi Criteria Decision Making Technique for Evaluation and ...

引用

2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2022

作者： Jassim Al-Shamary, Aidel Kadum Yas, Qahtan M. Badr, Aymen Mudheher Shalabi, Riyad Al Aldulaimi, Saeed Hameed Uninversity of Diyala Department of Mechanical Engineering Baqubah Iraq University of Diyala Department of Computer Science Baqubah Iraq Digital Research Center of Sfax Laboratory of Signals SysteMs ARtificial Intelligence and Networks Sfax University Sfax Tunisia Bahrain

ISBN: (数字)9781665469197

ISBN: (纸本)9781665469197

the composite material is considered basic material in various fields nowadays. Many companies have produced different types of this product according to specific criteria. This paper aims to present a new methodology for evaluation and selection based on multi criteria decision making (MCDM) techniques. A novelty claims by using an evaluation matrix (EM) to evaluate sandwich composite materials performance. The main issue of the evaluation of sandwich composite materials is performed by finding suitable criteria for performance metrics and the trade-off among the different types of composite materials. The methodology implemented in two steps;1) Creation decision matrix by calculating the data based on the five alternatives, 2) MCDM approach adapted by integrating between AHP and TOPSIS techniques. The finding outcome of the comparison of external with internal aggregation values to select the ideal sandwich composite materials was 5mm/5mm/5mm sample at 10J of threshold which is most recommended, whereas the 15mm sample at 25J of threshold obtained the lowest value, and it is the worst case. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Traffic Signal Control for Large-Scale Urban Traffic networks: Real-World Experiments using Vision-based Sensors

Traffic Signal Control for Large-Scale Urban Traffic Network...

引用

International Conference on Control and Automation (ICCA)

作者： Jiho Park Tong Liu Chieh Wang Hong Wang Qichao Wang Zhong-Ping Jiang Department of Electrical and Computer Engineering Control and Networks Lab Tandon School of Engineering New York University Brooklyn NY USA Oak Ridge National Laboratory Oak Ridge TN USA National Renewable Energy Laboratory Computational Science Center Golden CO USA

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Effective control of traffic signals plays a critical role in ensuring smooth vehicle flow in urban areas. Expertly engineered traffic signal controllers can considerably minimize travel delays and enhance sustainability. In this paper, the team proposes the Model Predictive Control (MPC) traffic signal control strategy using real-time traffic flow data from a vision-based camera as feedback information. Also, a realistic signal timing plan that considers National Electrical Manufacturers Association (NEMA) constraints has been developed to be applied to real-world scenarios. The primary aim is to reduce the number of vehicles across all links in the controlled area, thereby optimizing traffic flow and reducing energy consumption. To validate the proposed method, several real-life experiments were conducted at 24 intersections in Chattanooga, Tennessee, by collaborating with traffic field engineers. These experiments demonstrated significant performance improvements in comparison to the existing method.

关键词： Energy consumption Urban areas Decentralized control Data processing Real-time systems Sensors Delays

来源：评论

学校读者我要写书评

暂无评论

Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents

arXiv

引用

arXiv 2024年

作者： Ning, Kaiwen Chen, Jiachi Zhang, Jingwen Li, Wei Wang, Zexu Feng, Yuming Zhang, Weizhe Zheng, Zibin The School of Software Engineering Sun Yat-Sen University Peng Cheng Laboratory China The School of Software Engineering Sun Yat-Sen University China The School of Computer Science and Technology Harbin Institute of Technology China Peng Cheng Laboratory China The Department of New Networks Peng Cheng Laboratory China

Artificial intelligence (AI) agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in Large Language Models (LLMs) have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompt techniques. This advancement has significantly extended the capabilities of LLMs, positioning LLM-based AI Agents as an important research area. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behavior and expected outcomes can lead to defects, such as tool invocation failures and task execution errors. These issues introduce specific risks, leading to various defects in LLM-based AI Agents, including service interruptions and incorrect output. Despite the importance of these issues, there is a lack of systematic work that focuses on analyzing LLM-based AI Agents to uncover defects in their code. To address this gap, we present the first study focused on identifying and detecting defects in LLM Agents. We collected and analyzed 6, 854 relevant posts from StackOverflow to define and classify eight types of agent defects. For each defect type, we provided detailed descriptions and illustrated with an example. Then, we designed a static analysis tool, named Agentable, to detect the defined defects. Agentable leverages Code Property Graphs (CPGs) and LLMs to analyze Agent workflows by efficiently identifying specific code patterns and analyzing natural language descriptions. To evaluate Agentable, we constructed two datasets: AgentSet, which consists of 84 real-world Agent projects, and AgentTest, which contains 78 Agent projects specifically designed to include various types of defect

关键词： Autonomous agents

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：