检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Xiaoqin Ma, Xusen Hou, Xianxu Ding, Meidan Li, Yudong Chen, Junliang Chen, Wenting Peng, Xiaoyang Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China AIAC Xi’an Jiaotong-Liverpool University China Tsinghua University China The Hong Kong Polytechnic University Hong Kong City University of Hong Kong Hong Kong Sun Yat-sen University China

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://***/CVI-SZU/FaceBench. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

Vulnerability Detection with Graph Simplification and Enhanc...

引用

International Conference on Software engineering (ICSE)

作者： Xin-Cheng Wen Yupan Chen Cuiyun Gao Hongyu Zhang Jie M. Zhang Qing Liao School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory and Guangdong Provincial Key Laboratory Novel Security Intelligence Technologies School of Big Data and Software Engineering Chongqing University China Department of Informatics King's College London UK Peng Cheng Laboratory

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs; 2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dark-state solution and symmetries of the two-qubit multimode asymmetric quantum Rabi model

arXiv

引用

arXiv 2023年

作者： Lei, Ze-Feng Tian, Junlong Peng, Jie Hunan Key Laboratory for Micro-Nano Energy Materials and Devices School of Physics and Optoelectronics Xiangtan University Hunan411105 China Department of Electronic Science College of Big Data and Information Engineering Guizhou University Guiyang550025 China

We study the two-qubit asymmetric quantum Rabi model (AQRM) and find its dark-state solution. Such solutions have at most one photon and constant eigenenergy in the whole coupling regime, causing level crossings in the spectrum, although there is no explicit conserved quantity except energy. We find an operator in the eigenenergy basis to label all the degeneracies with its eigenvalues, and compare it with the well-known hidden symmetry which exists when bias parameter ϵ is a multiple of half of the resonator frequency ω. Extended to the multimode case, we find symmetries related with conserved bosonic number operators, which also cause level crossings. This provides a perspective for symmetry studies on generalized Rabi models. © 2023, CC BY.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Framework for Autonomous Vehicle Testing Using Semantic Models

A Framework for Autonomous Vehicle Testing Using Semantic Mo...

引用

IEEE International Conference on Artificial Intelligence Testing (AITest)

作者： Yejun He Muslim Razi Jerry Gao Chuanqi Tao Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Computer Engineering Department and Applied Data Science Department San Jose State University San Jose USA

With the rapid development of big data and artificial intelligence, autonomous vehicles (AV) have achieved great success in diverse application domains. Although the current development of autonomous driving technology has been greatly improved, the accident rate of driverless vehicles still rises. Therefore, how to ensure the quality of AVs using different testing technologies has become an important issue. Traditional testing approaches such as decision tables and state charts struggle with diversified test inputs. Hence, there is a strong demand for new test models for AV testing. In this paper, we present a model-based testing framework that utilizes semantic trees and 3-dimensional (3D) test tables to model driving scenarios into individual test cases. Using the proposed framework, we generate fine-grained examples corresponding to the real world. Also, we evaluate the behavior of the Apollo AV system in 30 scenarios in SVL simulator. The results show that the scenarios generated by our framework can cover most conditions occurring, thus addressing the challenge of testing AVs for safety and reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WikiIns: A High-Quality dataset for Controlled Text Editing by Natural Language Instruction

arXiv

引用

arXiv 2023年

作者： Chen, Xiang Li, Zheng Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University China Center for Data Science Peking University China The MOE Key Laboratory of Computational Linguistics Peking University China Schools of Electronic Engineering and Computer Science Peking University China

Text editing, i.e., the process of modifying or manipulating text, is a crucial step in human writing process. In this paper, we study the problem of controlled text editing by natural language instruction. According to a given instruction that conveys the edit intention and necessary information, an original draft text is required to be revised into a target text. Existing automatically constructed datasets for this task are limited because they do not have informative natural language instruction. The informativeness requires the information contained in the instruction to be enough to produce the revised text. To address this limitation, we build and release WikiIns, a high-quality controlled text editing dataset with improved informativeness. We first preprocess the Wikipedia edit history database to extract the raw data (WikiIns-Raw). Then we crowdsource high-quality validation and test sets, as well as a small-scale training set (WikiIns-Gold). With the high-quality annotated dataset, we further propose automatic approaches to generate a large-scale "silver" training set (WikiIns-Silver). Finally, we provide some insightful analysis on our WikiIns dataset, including the evaluation results and the edit intention analysis. Our analysis and the experiment results on WikiIns may assist the ongoing research on text editing. The dataset, source code and annotation guideline are available at https: //***/CasparSwift/WikiIns. Copyright © 2023, The Authors. All rights reserved.

关键词： Silver

来源：评论

学校读者我要写书评

暂无评论

An Improved Hybrid Switching Scheme for UAV-to-Ground ACM FSO System

An Improved Hybrid Switching Scheme for UAV-to-Ground ACM FS...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Qianwu Zhang Boyang Liu Guanwen Chen Shucheng Zhan Zhiyu Li Jing Zhang Ning Jiang Bingyao Cao Zhengxuan Li Key Laboratory of Specialty Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan China

An improved hybrid switching scheme is proposed for UAV-to-Ground ACM FSO system. Simulation results show SNR switching threshold deviation is reduced by 3.65 dB in strong turbulence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on Harmonic Elimination after LED Lamp Combination

Study on Harmonic Elimination after LED Lamp Combination

引用

第34届中国控制与决策会议

作者： Xu Jiechuan Ma Hongyan Dou Jiaming Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education

As LED(Light Emitting Diode) is widely used in distribution grids,the power quality problems caused by their harmonics injected into the grid are becoming more and more prominent,so it is necessary to study the harmonic emission characteristics of new energy-saving ***,it is very important to study the harmonic emission characteristics of new energy-saving ***,three kinds of LED simulation driver circuits are built in this paper,and the simulation results show that the harmonic emission characteristics of different driver circuits exist ***,the harmonic can be effectively reduced by the combination of three LED simulation driver ***,the experimental combination test of energy-saving lamps are carried *** results reveal that different combinations of lamps show different harmonic attenuation levels,and the harmonic currents in lighting system can be attenuated by combining specific types of lamps,thus reducing the fire *** harmonic control method has application value in engineering design.

关键词： LED Driver circuit Harmonic emission characteristics Lighting system

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

Downstream-agnostic Adversarial Examples

引用

International Conference on Computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Qing Gao, Qian Fan, Jun Zhang, Zhiqiang 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 Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd. No.1999 Shunhua road Shandong Jinan250101 China

ISBN: (纸本)9798350368741

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN-a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model's effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets. © 2025 IEEE.

关键词： graph contrastive learning graph neural networks recommender systems self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Movable Antennas for Wireless Networks

arXiv

引用

arXiv 2025年

作者： Zhu, Lipeng Ma, Wenyan Mei, Weidong Zeng, Yong Wu, Qingqing Ning, Boyu Xiao, Zhenyu Shao, Xiaodan Zhang, Jun Zhang, Rui Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Chengdu611731 China National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China School of Electronic and Information Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada State Key Laboratory of CNS/ATM MIIT Key Laboratory of Complex-field Intelligent Sensing Beijing Institute of Technology Beijing100081 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China

Movable antenna (MA) has been recognized as a promising technology to enhance the performance of wireless communication and sensing by enabling antenna movement. Such a significant paradigm shift from conventional fixed antennas (FAs) to MAs offers tremendous new opportunities towards realizing more versatile, adaptive and efficient next-generation wireless networks such as 6G. In this paper, we provide a comprehensive tutorial on the fundamentals and advancements in the area of MA-empowered wireless networks. First, we overview the historical development and contemporary applications of MA technologies. Next, to characterize the continuous variation in wireless channels with respect to antenna position and/or orientation, we present new field-response channel models tailored for MAs, which are applicable to narrowband and wideband systems as well as far-field and near-field propagation conditions. Subsequently, we review the state-of-the-art architectures for implementing MAs and discuss their practical constraints. A general optimization framework is then formulated to fully exploit the spatial degrees of freedom (DoFs) in antenna movement for performance enhancement in wireless systems. In particular, we delve into two major design issues for MA systems. First, we address the intricate antenna movement optimization problem for various communication and/or sensing systems to maximize the performance gains achievable by MAs. Second, we deal with the challenging channel acquisition issue in MA systems for reconstructing the channel mapping between arbitrary antenna positions inside the transmitter and receiver regions. Moreover, we show existing prototypes developed for MA-aided communication/sensing and the experimental results based on them. Finally, the extension of MA design to other wireless systems and its synergy with other emerging wireless technologies are discussed. We also highlight promising research directions in this area to inspire future investigatio

关键词： Antenna arrays

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：