检索结果-内蒙古大学图书馆

Dual-frequency-range modulator based on a planar nested multiscale metasurface

Photonics Research 2025年第5期13卷 1390-1399页

作者： JING YUAN GUICHUAN XU ZHENGANG LU XINMENG ZHUANG HUANPING ZHOU HEYAN WANG LIN HAN JIUBIN TAN Center of Ultra-precision Optoelectronic Instrument Engineering Harbin Institute of Technology Key Laboratory of Ultra-precision Intelligent Instrumentation (Harbin Institute of Technology) Ministry of Industry and Information Technology Department of Materials Science and Engineering College of EngineeringPeking University

Multi-spectral and multi-functional optical components play a crucial role in fields such as high-speed communications and optical sensing. However, the interaction between different spectra and matter varies significantly,making it challenging to simultaneously achieve dynamic multi-spectral modulation capabilities. We designed a modulator based on a planar nested multiscale metasurface, incorporating silicon(Si) and perovskite as control materials, to modulate both microwave and terahertz(THz) ranges.

关键词： Absorbers Notch filters Optical components Optical elements Optical materials Optical networks

来源：评论

学校读者我要写书评

暂无评论

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection 38

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Ob...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Li, Haochen Zhang, Rui Yao, Hantao Zhang, Xin Hao, Yifan Song, Xinkai Li, Xiaqing Zhao, Yongwei Li, Ling Chen, Yunji Intelligent Software Research Center Institute of Software CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, ***-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is available at https://***/Therock90421/DA-Ada. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI computing Systems for Large Language Models Training

引用

计算机科学技术学报（英文版） 2025年第1期40卷 6-41页

作者：张振兴文渊博吕涵祺刘畅张蕊李夏青王超杜子东郭崎李玲周学海陈云霁 1School of Computer Science and Technology University of Science and Technology of China Hefei 230026 China 2State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China 3Cambricon Technologies Beijing 100191 China 4Shanghai Innovation Center for Processor Technologies Shanghai 201210 China 5Intelligent Software Research Center Institute of Software Chinese Academy of Sciences Beijing 100190 China 6University of Chinese Academy of Sciences Beijing 101408 China

In this paper,we present a comprehensive overview of artificial intelligence(AI)computing systems for large language models(LLMs)*** rapid advancement of LLMs in recent years,coupled with the widespread adoption of algorithms and applications such as BERT,ChatGPT,and DeepSeek,has sparked significant interest in this *** classify LLMs into encoder-only,encoder-decoder,and decoder-only models,and briefly analyze their training and infer-ence processes to emphasize their substantial need for computational *** operations depend heavily on AI-specific accelerators like GPUs(graphics processing units),TPUs(tensor processing units),and MLUs(machine learning units).However,as the gap widens between the increasing complexity of LLMs and the current capabilities of accelerators,it becomes essential to adopt heterogeneous computing systems optimized for distributed environments to manage the growing computational and memory requirements of *** delve into the execution and scheduling of LLM algo-rithms,underlining the critical role of distributed computing strategies,memory management enhancements,and boosting computational *** paper clarifies the complex relationship between algorithm design,hardware infrastructure,and software optimization,and provides an in-depth understanding of both the software and hardware infrastructure sup-porting LLMs training,offering insights into the challenges and potential avenues for future development and deployment.

关键词： artificial intelligence(AI)chip large language model(LLM) AI computing system accelerator

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Speech Lie Detection Algorithm Based on Multiple Features and Adaptive Threshold

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第6期52卷 2015-2021页

作者： Zheng, Shuailong Tao, Huawei Yu, Hang Xi, Ji Zhu, Chunhua Wang, Xuemei Key Laboratory for Grain Information Processing and Control Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making Henan University of Technology Zhengzhou450001 China Computer Information Engineering Changzhou Institute of Technology Jiangsu213000 China

The limited number of labeled samples can significantly affect the accuracy of speech lie detection systems. However, semi-supervised algorithms have been shown to effectively improve detection performance under such constraints. To address this challenge, this paper proposes a semi-supervised speech lie detection algorithm that utilizes multiple features and adaptive thresholds. First, through comparative analysis, this paper identifies 312-dimensional acoustic features and 768-dimensional self-supervised features as the key elements of lie detection. Then, these acoustic features are processed using a bidirectional long short-term memory network (Bi-LSTM), which obtains comprehensive information by analyzing acoustic statistical features in both forward and backward directions. Subsequently, this paper develops a semi-supervised feature fusion module (BSFM) to extract deeper insights from basic features and achieves adaptive feature fusion through targeted training. In addition, based on a detailed analysis of the distribution characteristics of lie detection samples, this paper proposes an improved Freematch algorithm to better utilize unlabeled data. Experimental results show that the proposed algorithm outperforms most existing methods on the self-built H-Wolf dataset and the Columbia/SRI/Colorado Corpus (CSC). © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

UAV Spectrum Sensing against SSDF Attacks under Transmission Errors 2

UAV Spectrum Sensing against SSDF Attacks under Transmission...

引用

2nd IEEE International Conference on Signal, information and Data Processing, ICSIDP 2024

作者： Li, Huan Li, Ruide Wu, Jinghe Wen, Xiaowen Zhang, Xianchao An, Jianping Beijing Institute of Technology School of Cyberspace Security Beijing China Beijing Institute of Technology School of Information and Electronics Beijing China Yangtze Delta Region Academy Beijing Institute of Technology Jiaxing China Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing China

ISBN: (纸本)9798331515669

Unmanned aerial vehicles (UAVs) spectrum sensing is susceptible to Spectrum Sensing Data Falsification (SSDF) attacks, which pose a threat to its data security. However, most existing SSDF defense strategies overlook transmission errors between secondary users (SUs) and fusion center (FC). Hence, this study introduces a reputation-based defense method against SSDF attacks for UAV spectrum sensing, accounting for potential transmission errors between UAVs and FC. Based on the probability of each UAV reporting correct sensing results, we assign a reputation value to each UAV and exclude those with a value lower than or equal to the threshold from participating in collaborative spectrum sensing. To enhance precision, we calculate the individual detection probability for each UAV. By evaluating performance under the same sensing environment and considering transmission errors, we compared our method with an error-free SSDF defense approach that ignores these errors. Simulation results confirm that calculating the individual detection probability yields more precise results, and our proposed method is more effective in distinguishing legitimate users. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An embedded vertical‐federated feature selection algorithm based on particle swarm optimisation

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 734-754页

作者： Yong Zhang Ying Hu Xiaozhi Gao Dunwei Gong Yinan Guo Kaizhou Gao Wanqiu Zhang School of Information and Control Engineering China University of Mining and TechnologyXuzhouChina The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchunChina School of Computing University of Eastern FinlandKuopioFinland The Macao Institute of Systems Engineering Macao University of Science and TechnologyTaipaChina

In real life,a large amount of data describing the same learning task may be stored in different institutions(called participants),and these data cannot be shared among par-ticipants due to privacy *** case that different attributes/features of the same instance are stored in different institutions is called vertically distributed *** pur-pose of vertical‐federated feature selection(FS)is to reduce the feature dimension of vertical distributed data jointly without sharing local original data so that the feature subset obtained has the same or better performance as the original feature *** solve this problem,in the paper,an embedded vertical‐federated FS algorithm based on particle swarm optimisation(PSO‐EVFFS)is proposed by incorporating evolutionary FS into the SecureBoost framework for the first *** optimising both hyper‐parameters of the XGBoost model and feature subsets,PSO‐EVFFS can obtain a feature subset,which makes the XGBoost model more *** the same time,since different participants only share insensitive parameters such as model loss function,PSO‐EVFFS can effec-tively ensure the privacy of participants'***,an ensemble ranking strategy of feature importance based on the XGBoost tree model is developed to effectively remove irrelevant features on each ***,the proposed algorithm is applied to 10 test datasets and compared with three typical vertical‐federated learning frameworks and two variants of the proposed algorithm with different initialisation ***-mental results show that the proposed algorithm can significantly improve the classifi-cation performance of selected feature subsets while fully protecting the data privacy of all participants.

关键词： Evolutionary optimization feature selection privacy protection vertical‐federated learning

来源：评论

学校读者我要写书评

暂无评论

A Blind Batch Encryption and Public Ledger-Based Protocol for Sharing Sensitive Data

引用

China Communications 2024年第1期21卷 310-322页

作者： Zhiwei Wang Nianhua Yang Qingqing Chen Wei Shen Zhiying Zhang School of Computer Sciences Nanjing University of Posts and TelecommunicationsNanjing 210023China Dept.of Intelligent Science and Information Law East China University of Political Science and LawShanghai 201620China Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal UniversityHaikou 571158China State Key Laboratory of Public Big Data Guizhou UniversityGuizhou 550025China Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Research Institute of Beijing University of Aeronautics and AstronauticsKunming 650233

For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and allows privacy information to be *** owners can tightly manage their data with efficient revocation and only grant one-time adaptive access for the fulfillment of the *** prove that our protocol is semanticallly secure,blind,and secure against oblivious requesters and malicious file *** also provide security analysis in the context of four typical attacks.

关键词： blind batch encryption data sharing onetime adaptive access public ledger security and privacy

来源：评论

学校读者我要写书评

暂无评论

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Mo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chang, Zhiyuan Li, Mingyang Wang, Junjie Liu, Yi Wang, Qing Liu, Yang State Key Laboratory of Intelligent Game Beijing China Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Nanyang Technological University Singapore

ISBN: (纸本)9798891761681

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt. We first conduct an empirical study on this issue, exploring the prevalence of catastrophic-neglect, potential mitigation strategies with feature enhancement, and the insights gained. Guided by the empirical findings, we propose an automated repair approach named Patcher to address catastrophic-neglect in T2I DMs. Specifically, Patcher first determines whether there are any neglected objects in the prompt, and then applies attention-guided feature enhancement to these neglected objects, resulting in a repaired prompt. Experimental results on three versions of Stable Diffusion demonstrate that Patcher effectively repairs the issue of catastrophic-neglect, achieving 10.1%-16.3% higher Correct Rate in image generation compared to baselines. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion 39

EDGE: Unknown-aware Multi-label Learning by Energy Distribut...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yuchen Xu, Qianqian Wang, Zitai Yang, Zhiyong He, Junwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)157735897X

Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is crucial to model the joint information among classes. To this end, JointEnergy, which is a representative multi-label OOD inference criterion, summarizes the logits of all the classes. However, we find that JointEnergy can produce an imbalance problem in OOD detection, especially when the model lacks enough discrimination ability. Specifically, we find that the samples only related to minority classes tend to be classified as OOD samples due to the ambiguous energy decision boundary. Besides, imbalanced multi-label learning methods, originally designed for ID ones, would not be suitable for OOD detection scenarios, even producing a serious negative transfer effect. In this paper, we resort to auxiliary outlier exposure (OE) and propose an unknown-aware multi-label learning framework to reshape the uncertainty energy space layout. In this framework, the energy score is separately optimized for tail ID samples and unknown samples, and the energy distribution gap between them is expanded, such that the tail ID samples can have a significantly larger energy score than the OOD ones. What's more, a simple yet effective measure is designed to select more informative OE datasets. Finally, comprehensive experimental results on multiple multi-label and OOD datasets reveal the effectiveness of the proposed method. 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

Visible single-pixel sensing based on a helicity-multiplexing metasurface

Visible single-pixel sensing based on a helicity-multiplexin...

引用

2023 Novel Optical Materials and Applications, NOMA 2023

作者： Wang, Wenli Yan, Rong Hao, Qun Hu, Yao Bian, Liheng Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology School of Optics and Photonics Beijing Institute of Technology Beijing100081 China MIIT Key Laboratory of Complex-field Intelligent Sensing Advanced Research Institute of Multidisciplinary Science School of Information and Electronics Beijing Institute of Technology Beijing100081 China

We present a visible single-pixel sensing system based on a helicity-multiplexing metasurface that can realize edge-enhanced and bright-field imaging. Results show that this hybrid system enables high-fidelity dual-mo... 详细信息

关键词： Pixels

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：