检索结果-内蒙古大学图书馆

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zhang, Fan Jin, Kebing Zhuo, Hankz Hankui School of Computer Science and Engineering Sun Yat-sen University Guangzhou China State Key Laboratory of Public Big Data Guizhou University Guiyang China

ISBN: (纸本)9781643685489

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture strict logic from free-form texts. In this paper, we propose a novel graph-based language model, Logical-GLM, to extract strict logic from free-form texts and then infuse into language models. Specifically, we first capture information from natural language instructions and construct logical probability graphs that generally describe domains. Next, we generate logical skeletons to guide language model training, infusing domain knowledge into language models. At last, we alternately optimize the searching policy of graphs and language models until convergence. The experimental results show that Logical-GLM is both effective and efficient compared with traditional language models, despite using smaller-scale training data and fewer parameters. Our approach can generate instructional texts with more correct logic owing to the internalized domain knowledge. Moreover, the search of logical graphs reflects the inner mechanism of the language models, which improves the interpretability of black-box models. © 2024 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PRESS: Defending Privacy in Retrieval-Augmented Generation via Embedding Space Shifting

PRESS: Defending Privacy in Retrieval-Augmented Generation v...

引用

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

作者： He, Jiaming Liu, Cheng Hou, Guanyu Jiang, Wenbo Li, Jiachen School of Computer Science and Engineering University of Electronic Science and Technology of China China College of Computer Science and Cyber Security Oxford Brookes College Chengdu University of Technology China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350368741

Retrieval-augmented generation (RAG) expands the capabilities of large language models (LLMs) in various applications by integrating relevant information retrieved from external data sources. However, the RAG systems are exposed to substantial privacy risks during the information retrieval process, leading to potential data leakage of private information. In this work, we present a Privacy-preserving Retrieval-augmented generation via Embedding Space Shifting (PRESS), systematically exploring how to protect privacy in RAG systems. Specifically, we first conduct proximal policy optimization (PPO) based training on pre-trained language models to generate target training samples. Then we employ a purposive shift fine-tuning on the text embedding model with the generated samples for guiding the RAG system to map potential privacy leaking queries to safe target in embedding space. Extensive experimental results on representative models and datasets demonstrate that our protection method achieves high defense performance with high efficiency while keeping the normal functionality of the RAG system. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-Guided Human Depth Image Inpainting Based on Diffusion Models 4

Edge-Guided Human Depth Image Inpainting Based on Diffusion ...

引用

4th IEEE International Conference on data Science and computer Application, ICDSCA 2024

作者： Xia, Shiji Du, Yi Zhang, Jingyi Yang, Zuopeng Wang, Yu Fu, Yue Liu, Ming Ding, Xie School of Computer and Information Engineering Shanghai Polytechnic University Shanghai China Data Intelligence Product Department Wonders Information Co. Ltd Shanghai China

ISBN: (纸本)9798350368239

In the context of depth images, fusing human segmentation images with depth background images provides critical data for human detection tasks, where accurate localization of the human head is a key indicator. However, in real-world scenarios with occlusions and complex backgrounds, human segmentation images often lack head pixels. This missing data leads to subpar performance in human recognition tasks for deep learning models. To address this issue, this paper proposes an efficient approach that combines edge detection, projection analysis, and template matching for upper-body localization and head identification. Additionally, a refined diffusion model is used to repair the human head edge mask obtained from the initial processing. The main advantage of this approach is its independence from complex deep learning model training. It integrates traditional image processing techniques, morphological analysis, and diffusion models, simplifying head localization and effectively avoiding interference from the shoulder and arm regions. This approach enables more accurate head localization and uses diffusion models to restore missing portions of the human head, thereby improving overall pose recognition accuracy. Experimental results demonstrate that the repaired depth images outperform the original images in human pose model training. When trained with the repaired images, detection accuracy (mAPVal50-95) and precision improved by 10.1% and 7.1%, respectively, significantly enhancing downstream object detection performance. These findings validate the effectiveness of the proposed method in repairing missing human head depth images. They further highlight its potential in improving pose recognition and object detection performance, offering reliable technical support for related tasks. ©2024 IEEE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction 30

A Semantic Mention Graph Augmented Model for Document-Level ...

引用

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

作者： Zhang, Jian Yang, Changlin Zhu, Haiping Lin, Qika Xu, Fangzhi Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an China National University of Singapore Singapore

ISBN: (纸本)9782493814104

Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from an unstructured document. The advanced approaches on DEAE utilize prompt-based methods to guide pre-trained language models (PLMs) in extracting arguments from input documents. They mainly concentrate on establishing relations between triggers and entity mentions within documents, leaving two unresolved problems: a) independent modeling of entity mentions;b) document-prompt isolation. To this end, we propose a semantic mention Graph Augmented Model (GAM) to address these two problems in this paper. Firstly, GAM constructs a semantic mention graph that captures relations within and between documents and prompts, encompassing co-existence, co-reference and co-type relations. Furthermore, we introduce an ensembled graph transformer module to address mentions and their three semantic relations effectively. Later, the graph-augmented encoder-decoder module incorporates the relation-specific graph into the input embedding of PLMs and optimizes the encoder section with topology information, enhancing the relations comprehensively. Extensive experiments on the RAMS and WikiEvents datasets demonstrate the effectiveness of our approach, surpassing baseline methods and achieving a new state-of-the-art performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Indian Gross Domestic Product Per Capita Prediction based on Economic Indicators 5

Indian Gross Domestic Product Per Capita Prediction based on...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Sarveswaran, M.G. Mahalakshmi, B. Vaishnav, Varun Mishra, Shruti Satapathy, Sandeep Kumar Mallick, Pradeep Kumar School of Computer Science & Engineering Vit University Tamilnadu Chennai India Centre for Advanced Data Science Vellore Institute of Technology Tamil Nadu Chennai India School of Computer Engineeing Kiit University Odisha India

ISBN: (纸本)9798331522100

This paper is about identifying the contributing socio-economic indicators that affect the Gross Domestic Product Per Capita of India with historical data from 1960 to 2021 and build a methodology to predict the Gross Domestic Product per capita based on the contributing factors. To predict India's GDP per capita, an ensemble prediction was used, which included Support Vector Regression (SVR), the Extreme Gradient Boosting Model, and the ARIMA Model. It is critical to forecast GDP per capita and its influencing factors for better policy formulation, resource allocation, risk management, investment decisions, long-term planning, social welfare, and other purposes. This paper could contribute to encouraging long-term economic growth and improve citizens' quality of life. The findings of this paper provide an in-depth understanding of the intricate relationship between socioeconomic indicators and Gross Domestic Product in India. © 2025 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Histological Image Diagnosis of Breast Cancer Based on Multi-Attention Convolution Neural Network

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 91-106页

作者： XU Wangwang XU Liangfeng LIU Ninghui LU Na Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Ministry of EducationHefei230601China School of Computer and Information Hefei University of TechnologyHefei230601China First Affiliated Hospital of Anhui Medical University Hefei230022China

Breast cancer is a serious and high morbidity disease in women,and it is the main cause of cancer death in ***,getting tested and diagnosed early can reduce the risk of *** present,there are clinical examinations,imaging screening and biopsies,among which histopathological examination is the gold ***,the process is complicated and time-consuming,and misdiagnosis may *** paper puts forward a classification framework based on deep learning,introducing multi-attention mechanism,selecting kernel convolution instead of ordinary convolution,and using different weights and combinations to pay attention to the accuracy index and growth rate of the *** addition,we also compared the learning rate *** function can fine-tune the learning rate to achieve good performance,using label softening to reduce the loss error caused by model error recognition in the label,and assigning different category weights in the loss function to balance the positive and negative *** used the BreakHis data set to automatically classify histological images into benign and malignant,four categories and eight *** results showed that the accuracy of binary classifications ranged from 98.23%to 98.83%,and that of multiple classifications ranged from 97.89%to 98.11%.

关键词： breast cancer deep learning attentional mechanism classification diagnosis

来源：评论

学校读者我要写书评

暂无评论

What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection 24

What's the Real: A Novel Design Philosophy for Robust AI-Syn...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Hai, Xuan Liu, Xin Tan, Yuan Liu, Gang Li, Song Niu, Weina Zhou, Rui Zhou, Xiaokang School of Information Science and Engineering Lanzhou University Lanzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Business Data Science Kansai University Osaka Japan

ISBN: (纸本)9798400706868

Voice is one of the most widely used media for information transmission in human society. While high-quality synthetic voices are extensively utilized in various applications, they pose significant risks to content security and trust building. Numerous studies have concentrated on AI-synthesized voice detection to mitigate these risks, with many claiming to achieve promising performance. However, recent research has demonstrated that fake voice detectors suffer from serious overfitting to speaker-irrelative features (SiFs) and cannot be used in real-world scenarios. In this paper, we analyze the limitations of existing fake voice detectors and propose a new design philosophy, guiding the detection model to prioritize learning human voice features rather than the difference between the human voice and the synthetic voice. Based on this philosophy, we propose a novel AI-synthesized voice detection framework named SiFSafer, which uses pre-trained speech representation models to enhance the learning of feature distribution in human voices and the adapter fine-tuning to optimize the performance. The evaluation shows that the average EERs of existing fake voice detectors in the ASVspoof datasets can exceed 20% if the SiFs like silence segments are removed, while SiFSafer achieves an EER of less than 8%, indicating that SiFSafer is robust to SiFs and strongly resistant to existing attacks. © 2024 ACM.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Research on Frame and Table Recognition Based on CAD drawings

Research on Frame and Table Recognition Based on CAD drawing...

引用

2024 China Automation Congress, CAC 2024

作者： Zhong, Hui Miao, Yuanman Lìaonìng Province Big Data Management and Analysisline Laboratory of Urban Construction School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9798350368604

In the process of drawing architectural drawings with AutoCAD software, enterprises will produce a large number of CAD drawings in DWG format. The tables of these CAD drawings contain rich textual information. These text information constitute the key data base of enterprise systematic management drawings. At present, the systematic management of drawing data needs to collect these sheet data, but the sheet data collection mainly depends on manual input, which leads to high error rate of data collection, huge workload, long compilation cycle and low work efficiency. The purpose of this paper is to discuss how to deal with these tables efficiently. Firstly, based on Revit secondary development, the frame recognition algorithm is proposed, which confirms the inner and outer frame by finding the largest rectangle and the second largest rectangle. In addition, the Teigha class library is used to extract text, so as to extract key data, so as to promote the collection, reuse and systematic management of product data. Through the processing of drawing frames and forms, it lays a good foundation for subsequent component identification. The method proposed in this paper has strong versatility and adaptability, and can basically realize the recognition of CAD drawing frame and form, and extract form text, and achieve higher accuracy and efficiency. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Scalable Algorithms for Densest Subgraph Discovery 39

Scalable Algorithms for Densest Subgraph Discovery

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Luo, Wensheng Tang, Zhuo Fang, Yixiang Ma, Chenhao Zhou, Xu Hunan University College of Computer Science and Electronic Engineering China The Chinese University of HongKong School of Data Science Shenzhen China

ISBN: (纸本)9798350322279

As a fundamental problem in graph data mining, Densest Subgraph Discovery (DSD) aims to find the subgraph with the highest density from a graph. It has been studied for several decades and found a large number of real-world applications, such as network community detection, regulatory motif discovery in DNA, graph index construction, and fake follower detection. Although there are many existing DSD algorithms, they are often not scalable or efficient to process large-scale graphs, since most of them are serial algorithms and can only leverage the computing resource of a single CPU core. To tackle these issues, in this paper we propose efficient parallel algorithms for solving the DSD problems on both undirected and directed graphs at scale. Our main idea is to use the k-cores (a kind of dense subgraph) to approximate the densest subgraph in the undirected graphs, and then propose efficient parallel algorithms for computing the cores by optimizing the iterative process and also reducing the number of iterations. We further extend this idea for directed graphs by introducing a novel concept, named w-induced subgraph, to avoid unnecessary enumerations of x or y when searching [x,y]-cores (a kind of directed dense subgraph to approximate the densest). To verify the scalability and efficiency of the proposed algorithms, we have conducted extensive experiments on 12 large real-world graphs, and four of them are billion-scale. The experimental results show that our proposed algorithms outperform the state-of-the-art algorithms on both undirected and directed graphs, in terms of scalability and efficiency. © 2023 IEEE.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Object-Centric World Model for Language-Guided Manipulation

arXiv

引用

arXiv 2025年

作者： Jeong, Youngjoon Chun, Junha Cha, Soonwoo Kim, Taesup Graduate School of Data Science Department of Electrical and Computer Engineering

A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to the impressive success of diffusion models. However, these models require substantial computational resources. To address these challenges, we propose a world model leveraging object-centric representation space using slot attention, guided by language instructions. Our model perceives the current state as an object-centric representation and predicts future states in this representation space conditioned on natural language instructions. This approach results in a more compact and computationally efficient model compared to diffusion-based generative alternatives. Furthermore, it flexibly predicts future states based on language instructions, and offers a significant advantage in manipulation tasks where object recognition is crucial. In this paper, we demonstrate that our latent predictive world model surpasses generative world models in visuo-linguo-motor control tasks, achieving superior sample and computation efficiency. We also investigate the generalization performance of the proposed method and explore various strategies for predicting actions using object-centric representations. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot programming

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：