检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhao, Qianhui Zhang, Li Liu, Fang Lian, Xiaoli Meng, Qiaoyuanhe Jiao, Ziqian Zhou, Zetong Zhang, Borui Guo, Runlin Li, Jia School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Key Lab of High Confidence Software Technology Peking University China

Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CODESWIFT, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CODESWIFT constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CODESWIFT reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CODESWIFT can reach up to 2.53× and 2.54× speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. Our code and data are available at https://***/r/CodeSwift. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

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

作者： Zhang, Yujun Chen, Yanqu Wang, Jiakai Hu, Jin Tao, Renshuai Liu, Xianglong State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (纸本)9798350368741

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression. © 2025 IEEE.

关键词： Automatic speech recognition natural noise pattern phoneme-level targeted universal adversarial examples

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep Learning System Testing 24th

A Comprehensive Review on Deep Learning System Testing

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Li, Ying Shan, Chun Liu, Zhen Liao, Shuyan Beijing Key Laboratory of Software Security Engineering Technology Beijing Institute of Technology Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China Computer School Beijing Information Science and Technology University Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9789819615476

Deep learning(DL) systems exhibit multiple behavioral characteristics such as correctness, robustness, and fairness. Ensuring that these behavioral characteristics function properly is crucial for maintaining the accuracy of DL systems’ outputs. As a specialized form of software, DL systems’ security testing techniques have increasingly become a focus of research in quality assurance. We analyze and organize the testing techniques for DL systems based on an investigation of the current state of the art both domestically and internationally. This paper categorizes existing approaches as component-oriented and attribute-oriented methods, providing a detailed review based on this classification. Additionally, we forecast the future development of testing techniques for DL systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Issue on Formal Methods and Models for System Design

引用

ACM Transactions on Embedded Computing Systems 2025年第3期24卷 1-3页

作者： Jens Brandt Indranil Saha Lijun Zhang Engineering and Computer Science Hochschule Niederrhein Krefeld Germany Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur India State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Multi-View Incongruity Learning for Multimodal Sarcasm Detection 31

Multi-View Incongruity Learning for Multimodal Sarcasm Detec...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guo, Diandian Cao, Cong Yuan, Fangfang Liu, Yanbing Zeng, Guangjie Yu, Xiaoyan Peng, Hao Yu, Philip S. Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798891761964

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model's generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Multi-Label Contrastive Learning by Leveraging Label Distribution

arXiv

引用

arXiv 2025年

作者： Chen, Ning Lyu, Shen-Huan Wu, Tian-Shuang Wang, Yanyan Tang, Bin Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and negative samples based on the overlap between labels and used them for label-wise loss balancing. However, these methods suffer from a complex selection process and fail to account for the varying importance of different labels. To address these problems, we propose a novel method that improves multi-label contrastive learning through label distribution. Specifically, when selecting positive and negative samples, we only need to consider whether there is an intersection between labels. To model the relationships between labels, we introduce two methods to recover label distributions from logical labels, based on Radial Basis Function (RBF) and contrastive loss, respectively. We evaluate our method on nine widely used multi-label datasets, including image and vector datasets. The results demonstrate that our method outperforms state-of-the-art methods in six evaluation metrics. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Compressing Model with Few Class-Imbalance Samples: An Out-of-Distribution Expedition

arXiv

引用

arXiv 2025年

作者： Wu, Tian-Shuang Lyu, Shen-Huan Chen, Ning Qu, Zhihao Ye, Baoliu Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In recent years, as a compromise between privacy and performance, few-sample model compression has been widely adopted to deal with limited data resulting from privacy and security concerns. However, when the number of available samples is extremely limited, class imbalance becomes a common and tricky problem. Achieving an equal number of samples across all classes is often costly and impractical in real-world applications, and previous studies on few-sample model compression have mostly ignored this significant issue. Our experiments comprehensively demonstrate that class imbalance negatively affects the overall performance of few-sample model compression methods. To address this problem, we propose a novel and adaptive framework named OOD-Enhanced Few-Sample Model Compression (OE-FSMC). This framework integrates easily accessible out-of-distribution (OOD) data into both the compression and fine-tuning processes, effectively rebalancing the training distribution. We also incorporate a joint distillation loss and a regularization term to reduce the risk of the model overfitting to the OOD data. Extensive experiments on multiple benchmark datasets show that our framework can be seamlessly incorporated into existing few-sample model compression methods, effectively mitigating the accuracy degradation caused by class imbalance. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Memetic Algorithm Based Feature Weighting for Metabolomics Data Classification

引用

Chinese Journal of Electronics 2025年第4期23卷 706-711页

作者： Jiarui Zhou Zexuan Zhu Zhen Ji College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China Shenzhen City Key Laboratory of Embedded System Design College of Computer Science and Software Engineering Shenzhen University Shenzhen China

A metaheuristic chain based memetic algorithm namely MCMA is proposed for the classification of metabolomics data. MCMA regards both global evolution and local search as equivalent elemental metaheuristics, and searches with a chain of metaheuristics performed alternatively on the target problem. A hidden Markov model based scheduling mechanism is employed in MCMA for the selection of metaheuristics. By using MCMA for optimizing the linkage weight vector, a feature weighting algorithm for metabolomics data is formed to identify relevant metabolite features and reveal their exact relationships with the given physiological states. An extreme learning machine based classifier is utilized in predicting the physiological states according to the weighted metabolite features. Experimental results on real metabolomics data of clinical liver transplantation demonstrate that the proposed feature weighting and classification method obtains better performance than the other compared algorithms.

关键词： Memetics Metabolomics Metaheuristics Urban areas Liver Prediction algorithms Search problems Physiology Vectors Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

MixSSC: Forward-Backward Mixture for Vision-based 3D Semantic Scene Completion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Meng Ding, Yan Liu, Yumeng Qin, Yunchuan Li, Ruihui Tang, Zhuo The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing100190 China

Vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, 3D modeling from a single view is an ill-posed problem, limited by the field of view and occlusion problems caused by image input. Moreover, existing methods tend to produce erroneous scene hallucinations and overly smooth boundary segmentation due to a lack of information. To address this problem, we propose MixSSC, which mixes the sparsity of forward projection with the denseness of depth-prior backward projection. The aim is to use sparse features to fill information-poor regions and dense features to enhance visible regions. Specifically, we develop the forward-backward mixture module, which enables the generation of scene mixture voxel representation by leveraging the benefits of both forward and backward projection. Subsequently, we design the semantic-spatial fusion module, which utilizes a coarse-to-fine approach to process mixture voxel features at the semantic-spatial level. Extensive experimental results on the SemanticKITTI, SSCBench-KITTI-360 and nuScenes datasets demonstrate the superiority of MixSSC. © 1991-2012 IEEE.

关键词： Semantic Segmentation

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：