检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Wei, Kaiwen Zhong, Jiang Zhang, Hongzhi Zhang, Di Jin, Li Yu, Yue Zhang, Jingyuan College of Computer Science Chongqing University China Kuaishou Inc. China Key Laboratory of Network Information System Technology Aerospace Information Research Institute Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Despite these advancements, previous research found that LLMs sometimes struggle with adhering to specific constraints (e.g., in specific place or at specific time), at times even overlooking them, which leads to responses that are either too generic or not fully satisfactory. Existing approaches attempted to address this issue by decomposing, rewriting input instructions, or reflecting on prior failings, yet they fall short in adequately emphasizing specific constraints and in unlocking the underlying knowledge (e.g., programming within the context of software development). In response, this paper proposes a simple yet effective method Chain-of-Specificity (CoS). Specifically, CoS iteratively emphasizes the specific constraints in the input instructions, unlocks knowledge within LLMs, and refines responses. Experiments conducted on publicly available and self-build complex datasets demonstrate that CoS outperforms existing methods in enhancing generated content especially for the specificity. Besides, as the number of specific constraints increase, other baselines falter, while CoS still performs well. Moreover, we show that distilling responses generated by CoS effectively enhances the ability of smaller models to follow the constrained instructions. © 2025 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

A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction 31

A Chain-of-Task Framework for Instruction Tuning of LLMs Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Xinpeng Xu, Bing Yang, Muyun Cao, Hailong Zhu, Conghui Zhao, Tiejun Lu, Wenpeng Faculty of Computing Harbin Institute of Technology Harbin China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China

ISBN: (纸本)9798891761964

Over-correction is a critical issue for large language models (LLMs) to address Grammatical Error Correction (GEC) task, esp. for Chinese. This paper proposes a Chain-of-Task (CoTask) framework to reduce over-correction. The CoTask framework is applied as multi-task instruction tuning of LLMs by decomposing the process of grammatical error analysis to design auxiliary tasks and adjusting the types and combinations of training tasks. A supervised fine-tuning (SFT) strategy is also presented to enhance the performance of LLMs, together with an algorithm for automatic dataset annotation to avoid additional manual costs. Experimental results demonstrate that our method achieves new state-of-the-art results on both FCGEC (in-domain) and NaCGEC (out-of-domain) test sets. © 2025 Association for Computational Linguistics.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

A Verifiable Decentralized Data Modification Mechanism Supporting Accountability for Securing Industrial IoT 24th

A Verifiable Decentralized Data Modification Mechanism Suppo...

引用

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

作者： Yang, Changsong Wu, Junfu Liang, Hai Ding, Yong Wang, Yujue Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China Institute of Cyberspace Technology HKCT Institute for Higher Education Hong Kong Hangzhou Innovation Institute of Beihang University Hangzhou China

ISBN: (纸本)9789819615247

The widespread application of Industrial Internet of Things (IIoT) has profoundly transformed modern industrial production methods. However, the large scale of industrial data, the diversity of data sources, and the heterogeneity of data structures make data maintenance exceptionally challenging. The editability techniques have been introduced into blockchain to leverage its distributed and editable features for data maintenance and management. However, existing solutions mainly focus on achieving editability while overlooking data management personnel’s privacy protection and lacking effective modification verification mechanisms to ensure data reliability. To address these issues, this paper proposes a verifiable decentralized data modification mechanism supporting accountability (DDMA) for securing IIoT. Our DDMA mechanism not only achieves the redactability of blockchain but also protects the privacy of data management personnel and provides reliable clues for subsequent accountability. Additionally, the DDMA mechanism offers an efficient method for modification verification, enabling rapid validation of whether on-chain data has been modified. Theoretical analysis demonstrates that DDMA meets the requirements of modification authorization, behavior traceability, and efficient modification verification. Experimental results indicate that DDMA can reduce modification and verification overheads. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Ownership Transfer Protocol for Cloud EMRs Auditing 24th

A Fine-Grained Ownership Transfer Protocol for Cloud EMRs A...

引用

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

作者： Wang, Yamei Zhang, Yuexin You, Weijing Ma, Yunru Wang, Derui Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou China School of Health Fujian Medical University Fuzhou China CSIRO’s Data61 Melbourne Australia

ISBN: (纸本)9789819615445

In cloud Electronic Medical Records (EMRs), a user’s medical records typically comprise various types of health-related sensitive data. When data ownership needs to be transferred, it is preferred to transfer the required data to target users, instead of transferring the entire records. Existing protocols cannot adequately address this issue. Therefore, we leverage the searchable encryption and propose a fine-grained ownership transfer protocol. Specifically, users in our protocol determine data blocks for ownership transfer based on keywords. Additionally, our protocol is designed for single-owner to multi-owner scenario, it is achieved by leveraging characteristics of threshold signatures and multi-signatures. The employment of threshold signatures and multi-signatures realizes flexible and less resource-intensive ownership transfer. Furthermore, we experimentally analyse the performance of our protocol, and compare it with relevant protocols. According to the comparisons, our protocol has more features with moderate resource consumptions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Confidence-Guided Feature Alignment for Cloth-Changing Person Re-identification 27th

Confidence-Guided Feature Alignment for Cloth-Changing Pers...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Huang, Sirong Zheng, Huicheng School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783031781094

Much progress has been made in the field of person re-identification, but changes in clothing have hindered the practical application of long-term person re-identification. Cloth-changing person re-identification (CC-ReID) aims to address this problem, with the main challenge being the extraction of discriminative features unrelated to clothing. Existing methods, which mainly focus on introducing clothing-irrelevant cues such as key points, contours, and 3D shapes, require additional modules for feature extraction, resulting in increased complexity and potential inaccuracies due to dependence on the performance of external models. Few studies directly use the original RGB images to make the model constantly focus on clothing-independent information. In this paper, we propose a Confidence-Guided Feature Alignment network (CGFA) for CC-ReID. Specifically, we design a confidence module that automatically learns to make confidence adjustments to fine-grained information, prompting the model to mine clothing-independent discriminative features without introducing other modal cues. By transferring knowledge, we encourage the model to learn discriminative identity features that are independent of clothing bias. As a result, the confidence module can be removed during the inference phase. The proposed simple but efficient method uses only RGB modality without additional cues, and can serve as a powerful baseline for CC-ReID to drive future research. Extensive experiments on the CC-ReID datasets demonstrate the effectiveness of the proposed method, which achieves state-of-the-art performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Zero-Shot Object Detection via Semantic Decoupling 24

Fine-Grained Zero-Shot Object Detection via Semantic Decoupl...

引用

8th International Conference on computer Science and Artificial Intelligence, CSAI 2024

作者： Duan, Lijuan Zhang, Zichen Gong, Zhi Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China School of Computer Science Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China

ISBN: (纸本)9798400718182

Recent deep learning models have advanced object detection capabilities, but their reliance on labeled data limits scalability. Fine-grained zero-shot detection remains challenging due to the need to generalize to unseen classes and distinguish subtle features. To address this, we propose Fine-Grained Zero-Shot Object Detection via Semantic Decoupling (ZSD-SD). Our approach introduces a semantic decoupling module to separate visual features into semantic-related and semantic-unrelated components, facilitating alignment between visual and semantic spaces. A semantic-visual learning module further decouples these features, enhancing visual representations relevant to external semantic knowledge. This semantic-related representation significantly improves zero-shot performance. Experiments on two fine-grained object detection datasets demonstrate that ZSD-SD achieves state-of-the-art results. © 2024 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Reflectance Recovery Guided Learning of Illumination-Invariant Features for Person Re-Identification 18th

Reflectance Recovery Guided Learning of Illumination-Invari...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Chen, Xianbiao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9789819610679

In real-world scenarios, the changes of illumination are noticeable and can significantly impact the performance of re-identification (ReID) algorithms. However, the existing person ReID methods predominantly concentrate on tackling challenges in scenarios with minimal illumination fluctuations. The key to tackling this issue is to extract illumination-invariant features. So we propose a joint learning framework which combines the recovery of reflectance map and extraction of illumination-invariant feature. By sharing parameters, the proposed module, which can be seamlessly detached during the inference phase, contributes to a reduction in inference computation time. We also introduce an adversarial learning mechanism, utilizing illumination category and person identity to facilitate the extraction of features that are invariant to illumination. Besides, due to the lack of person ReID dataset containing images under diverse lighting conditions, we construct a real-world dataset called ICReID in which images have drastic illumination changes. Extensive experiments demonstrate the effectiveness of the proposed method, which achieves significant performance on both synthetic and real datasets. © 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

A Byzantine Client Detection Method for Federated Learning Based on Encrypted Repeated Median Linear Regression 24

A Byzantine Client Detection Method for Federated Learning B...

引用

5th International Conference on computer Science and Management Technology, ICCSMT 2024

作者： Guo, Jinlong Yang, Ming Li, Huijuan Wu, Xiaoming He, Yunpeng Wang, Xin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Shandong Jinan China Shandong Evayinfo Technology Co. Ltd. Shandong Jinan China

ISBN: (纸本)9798400709999

Federated learning is an emerging distributed machine learning technology that allows participants to jointly train machine learning models locally without the need for large-scale data transmission and sharing, thereby greatly improving data security. However, some Byzantine clients may intentionally tamper with local model parameter updates with the intention of manipulating the global model's update direction, which can lead to a decline in the overall performance of federated learning. Besides, existing Byzantine client detection research is conducted in plain text, which will lead to the leakage of private information. To solve the above issues, we propose a Byzantine client detection method for federated learning based on encrypted repeated median linear regression. Specifically, it combines the repeated median linear regression algorithm with homomorphic encryption, which can detect and eliminate clients with Byzantine behavior in the ciphertext state, ensuring the security and reliability of the parameters in the entire federated learning process. Additionally, we also designed an adaptive gradient clipping method based on historical iteration to clip the gradient to a reasonable range, which can not only reduce communication and computing overhead, but also improve the convergence speed and stability of the model. Experiments show that the proposed method can maintain high accuracy under the influence of malicious behavior of Byzantine clients. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CurMIM: Curriculum Masked Image Modeling

CurMIM: Curriculum Masked Image Modeling

引用

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

作者： Liu, Hao Wang, Kun Han, Yudong Wang, Haocong Hu, Yupeng Wang, Chunxiao Nie, Liqiang School of Software Shandong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798350368741

Masked Image Modeling (MIM), following "mask-and-reconstruct" scheme, is a promising self-supervised method to learn scalable visual representation. Studies indicate that selecting an effective mask strategy is vital for MIM. However, existing approaches often rely on static pre-defined priors, which limit their ability to adapt mask strategies dynamically for network optimization. In this paper, we focus on the learning process of the network and introduce human-like curriculum into MIM for dynamic representation refinement, and propose an end-to-end framework Curriculum Masked Image Modeling (CurMIM). CurMIM consists of two components: Mask Priority Measurer, which acts as a curriculum learner to determine mask priority values using the network's intrinsic state information, and Dual Adaptive Selector, which serves as a curriculum scheduler to create effective masks based on these values. With negligible extra parameters, our curriculum-based method consistently establishes noticeable improvements across varying model sizes and benchmarks, showing effectiveness and generalization. © 2025 IEEE.

关键词： Curriculum Learning Image Representation Masked Image Modeling Visual Pre-training

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

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：