检索结果-内蒙古大学图书馆

17th International Conference on Combinatorial Optimization and Applications, COCOA 2024

作者： Yuan, Jing Tang, Shaojie Department of Computer Science and Engineering University of North Texas Denton United States Center for AI Business Innovation Department of Management Science and Systems University at Buffalo Buffalo United States

ISBN: (纸本)9789819644476

Most of existing studies on submodular maximization focus on selecting a subset of items that maximizes a single submodular function. However, in many real-world scenarios, we might have multiple user-specific functions, each of which models the utility of a particular type of user. In these settings, our goal would be to choose a set of items that performs well across all the user-specific functions. One way to tackle this problem is to select a single subset that maximizes the sum of all of the user-specific functions. Although this aggregate approach is efficient in the sense that it avoids computation of sets for individual functions, it really misses the power of personalization - for it does not allow to choose different sets for different functions. In this paper, we introduce the problem of personalized submodular maximization with two candidate solutions. For any two candidate solutions, the utility of each user-specific function is defined as the better of these two candidates. Our objective is, therefore, to select the best set of two candidates that maximize the sum of utilities of all the user-specific functions. We have designed effective algorithms for this problem. We also discuss how our approach generalizes to multiple candidate solutions, increasing flexibility and personalization in our solution. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models 31

Converging to a Lingua Franca: Evolution of Linguistic Regio...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zeng, Hongchuan Han, Senyu Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this ability remain unclear. We observed that the neuron activation patterns of LLMs exhibit similarities when processing the same language, revealing the existence and location of key linguistic regions. Additionally, we found that neuron activation patterns are similar when processing sentences with the same semantic meaning in different languages. This indicates that LLMs map semantically identical inputs from different languages into a "Lingua Franca", a common semantic latent space that allows for consistent processing across languages. This semantic alignment becomes more pronounced with training and increased model size, resulting in a more language-agnostic activation pattern. Moreover, we found that key linguistic neurons are concentrated in the first and last layers of LLMs, becoming denser in the first layers as training progresses. Experiments on BLOOM and LLaMA2 support these findings, highlighting the structural evolution of multilingual LLMs during training and scaling up. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities. The codes are available at: https://***/X-LANCE/LinguaFranca. © 2025 Association for Computational Linguistics.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Biomedical Knowledge Graph Construction and Querying: An Advanced NLP Approach 25

Leveraging Large Language Models for Biomedical Knowledge Gr...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Suramya Jadhav Suki Perumal Yasmin Tadavi Bikshita Dash Srinivasan Parthiban Computer Engineering Department Pune Institute of Computer Technology Pune India Department of CSE (AI & ML) PES University Bangalore India Department of Data Science and Engineering Indian Institute of Science Education and Research Bhopal India Aarupadai Veedu Medical College & Hospital Centre for AI in Medicine Vinayaka Missions Research Foundation Puducherry India

ISBN: (纸本)9798400713316

This paper introduces a novel methodology for constructing a comprehensive biomedical knowledge graph by applying advanced Natural Language Processing (NLP) techniques. By leveraging Large Language Models (LLMs) and a multifaceted prompt engineering approach, we effectively perform Named Entity Recognition (NER) and Relation Extraction (RE) on biomedical literature, targeting entities such as diseases, drugs, proteins, procedures, and symptoms. Our methodology incorporates eight distinct prompt engineering strategies for NER and a standardized approach for RE, facilitating the extraction of intricate inter-entity relationships. The resulting knowledge graph amalgamates diverse data sources into a unified framework, enabling efficient querying, visualization, and analysis of biomedical information. Furthermore, we present an innovative query processing pipeline that integrates GPT-3.5 turbo with the knowledge graph, allowing users to interact with the graph through natural language. This integrated system empowers the discovery of novel correlations, accelerating scientific research and fostering interdisciplinary collaboration. This represents a substantial contribution to the field of biomedical knowledge graph construction, offering a robust platform for accelerating scientific discovery and informing clinical decision-making.

关键词： knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

Self-Consistent Model-based Adaptation for Visual Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhou, Xinning Ying, Chengyang Feng, Yao Su, Hang Zhu, Jun Department of Computer Science & Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China

Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy’s representations with hand-crafted augmentations. In this work, we propose Self-Consistent Model-based Adaptation (SCMA), a novel method that fosters robust adaptation without modifying the policy. By transferring cluttered observations to clean ones with a denoising model, SCMA can mitigate distractions for various policies as a plug-and-play enhancement. To optimize the denoising model in an unsupervised manner, we derive an unsupervised distribution matching objective with a theoretical analysis of its optimality. We further present a practical algorithm to optimize the objective by estimating the distribution of clean observations with a pre-trained world model. Extensive experiments on multiple visual generalization benchmarks and real robot data demonstrate that SCMA effectively boosts performance across various distractions and exhibits better sample efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

From Generalist to Specialist: A Survey of Large Language Models for Chemistry 31

From Generalist to Specialist: A Survey of Large Language Mo...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Han, Yang Wan, Ziping Chen, Lu Yu, Kai Chen, Xin X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic survey specifically focused on chemistry-oriented LLMs. In this paper, we outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs, we also conceptualize chemistry LLMs as agents using chemistry tools and investigate their potential to accelerate scientific research. Additionally, we conclude the existing benchmarks to evaluate chemistry ability of LLMs. Finally, we critically examine the current challenges and identify promising directions for future research. Through this comprehensive survey, we aim to assist researchers in staying at the forefront of developments in chemistry LLMs and to inspire innovative applications in the field. © 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

Multi-agent Scheduling for Shared Manufacturing Systems 6

Multi-agent Scheduling for Shared Manufacturing Systems

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Duran, Ege Ozturk, Cemalettin O'Sullivan, Barry SFI Centre for Research Training in AI School of Computer Science IT University College Cork Ireland Department of Process Energy & Transport Engineering Munster Technological University Cork Ireland Insight SFI Research Centre for Data Analytics School of Computer Science & IT University College Cork Ireland

Advances in digitization and resource-sharing business models have created new opportunities for manufacturing companies, enhancing competitiveness and resilience. However, these benefits bring computational challenges in efficiently planning and scheduling shared resources. Therefore, there is a need for scalable and quick solutions for practical applications. Shared manufacturing systems share characteristics with parallel machine scheduling, allowing for the application of advancements from this domain. This research focuses on Multi-Agent Parallel Machine Scheduling (MAPMS) in shared manufacturing, specifically addressing scenarios involving two parallel machines and distinct agents managing exclusive, set of non-overlapping orders. The study introduces a novel multi-objective mixed integer programming (MIP) model for order scheduling across multiple facilities, accounting for sequence-dependent setup times between orders. It also proposes a new heuristic method designed for industrial use. Benchmark instances demonstrate the practicality of both the MIP model and heuristic, contributing valuable insights into MAPMS challenges in shared manufacturing environments. © 2025 The Authors.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Smart Mood Detection: Real-Time Emotion Analysis for Human-computer Interaction Using Deep Learning

Smart Mood Detection: Real-Time Emotion Analysis for Human-C...

引用

Artificial Intelligence and Data engineering (aiDE), International Conference on

作者： Chandrappa S Tapabrata Banerjee Sohan Saha Mohd Zaid Aditya Pai H Guru Prasad M S Rajesh I S Dept. of Computer Science and Engineering JAIN (Deemed to-be University) Bengaluru India Dept. of Computer Science and Engineering(AI and DE) JAIN (Deemed to-be University) Bengaluru India Department of CSE MIT Art Design and Technology University Pune India Department of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Dept. of AI & ML BMS Institute of Technology and Management Bengaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

A convolutional neural network (CNN)-based face emotion recognition system that analyzes human emotions in real-time, including happy, sorrow, rage, and surprise, is described. Existing approaches often struggle with accurately recognizing subtle or complex emotions due to limited feature extraction capabilities and the need for large, diverse training datasets. Additionally, they face challenges in adapting to real-world conditions, such as variations in lighting, angles, and occlusions. In order to improve the model's generalizability, the proposed research used a preprocessing pipeline that included gray scale conversion, scaling, normalization, and augmentation techniques including rotation and flipping on a labeled and balanced dataset of facial photos. Dropout and regularization techniques were used to reduce over fitting, and the CNN architecture was meticulously adjusted to maximize speed. High accuracy and resilience across emotion categories are demonstrated by preliminary results, indicating the model's potential for real-world uses in security surveillance, healthcare, and human-computer interaction.

关键词： Human computer interaction Training Emotion recognition Mood Face recognition Surveillance Real-time systems Convolutional neural networks Security Resilience

来源：评论

学校读者我要写书评

暂无评论

Advanced Detection of Diabetic Foot Ulcers Using Hamiltonian Quantum GANs and Cell Attention Networks, with Genghis Khan Shark Optimization

引用

Biomedical Materials and Devices 2025年 1-17页

作者： Bapu, B. R. Tapas Sivamuni, Kalaimagal Samiappan, Dhandapani Sathiya, R.R. Department of Electronics and Communication Engineering S.A. Engineering College Poonamallee-Avadi Main Road Thiruverkadu Tamil Nadu Chennai 600077 India Department of AI & DS Panimalar Engineering College Varadharajapuram Poonamallee Tamil Nadu Chennai 6000123 India Department of Electronics and Communication Engineering Saveetha Engineering College Tamil Nadu Chennai 602105 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Diabetic Foot Ulcers (DFUs) are a severe difficulties of diabetes, often resulting from peripheral vascular disease, neuropathy, and poor glycemic control. If left undetected, DFUs can lead to severe infections, amputations, and increased mortality rates. Despite advancements in deep learning for medical image analysis, existing DFU detection methods suffer from low accuracy, high false-positive rates, and limited generalizability, making them unsuitable for real-world clinical deployment. To point out this challenge, this study proposes a novel DFU detection framework Cell Attention Networks with Genghis Khan Shark Optimization (CANet-GKSOpt) which integrates multiple cutting-edge ai techniques to enhance diagnostic precision. The proposed method utilizes Block-Batching Domain-Guided Filtering (2B-DGF) for noise reduction and image enhancement, followed by feature extraction using Hamiltonian Quantum Generative Adversarial Networks (HQGANet) to capture complex ulcer patterns. Cell Attention Networks (CANet) are then employed for refined classification by focusing on critical image regions. To further optimize accuracy and computational efficiency, the Genghis Khan Shark Optimization (GKSO) algorithm is applied for parameter tuning. The model is evaluated on the DFU2020 dataset and achieves a satisfying accuracy around 99% and 99.8% of sensitivity, significantly outperforming existing state-of-the-art methods. These results demonstrate the robustness of CANet-GKSOpt in accurately detecting DFUs, reducing false positives, and improving classification efficiency. The proposed approach contributes to the evolution of a highly effective ai-assisted diagnostic tool, which, with further validation on multi-center datasets and real-world clinical settings, has the potential to revolutionize DFU detection and management. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Block-batching domain-guided filtering cell attention networks DFUs detection Genghis Khan shark optimization Hamiltonian quantum generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Empowering Fake News Detection Through Innovative Hybrid Deep Learning-Based Approach

Empowering Fake News Detection Through Innovative Hybrid Dee...

引用

Computing for Sustainability and Intelligent Future (COMP-SIF), International Conference on

作者： A Suresh R M Mallika S Gireesh G Hari Kiran Singh E S Jeevanandham A Hemalatha Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Puttur India Department of Computer Science and Engineering (AI&DS) Siddharth Institute of Engineering & Technology Puttur India

ISBN: (数字)9798331538538

ISBN: (纸本)9798331538545

The essence of getting information to the populace in the shortest time possible through social media and other interactive technologies has made it easier for fake news to thrive hence creating a menace to any society as well as its decision-making systems. This research work presents a sound ai-based approach to classify fake news using DL algorithms embedded within a CNN-BiLSTM model. Using the ISOT dataset, the comparison of the outcomes achieved by the proposed model with the original models shows that the proposed model has the highest accuracy score of 94.07%, a precision of 93.50%, a recall of 94.60%, and an F1-score of 94.00%. The proposed hybrid model architecture of CNN for spatial feature extraction and BiLSTM for capturing contextual dependencies that are essential for text analysis and have relatively high accuracy compared to conventional ml algorithms, including CNN, RNN, LSTM, and other DL methods. The proposed approach is verified by a set of comprehensive measures, including ROC curve analysis and various training-validation metrics that reveal the effectiveness of the presented approach in overcoming the challenges of fake news identification.

关键词： Fake news Accuracy Feature extraction Bidirectional long short term memory Convolutional neural networks Data models computer science Vectors Computational modeling Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Exploiting Differential-Based Data Encoding for Enhanced Query Efficiency 25

Exploiting Differential-Based Data Encoding for Enhanced Que...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Liu, Fangxin Wang, Zongwu Xu, Peng Huang, Shiyuan Jiang, Li Department of Computer Science and Engineering Shanghai Jiao Tong University China Shanghai Qi Zhi Institute China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University China

ISBN: (纸本)9798400706356

Storing large-scale high-dimensional data, which is rapidly generated by both industry and academia, poses substantial challenges, primarily in terms of storage and maintenance costs. While data compression techniques offer a potential solution to these challenges, they must overcome two critical hurdles: 1) preserving data integrity within lossless bounds and 2) maintaining query performance on compressed *** address the above challenges, we propose a novel approach based on differential techniques that combine high-dimensional data compression with an efficient query engine. Specifically, Our methodology begins by employing vector quantization to transform high-dimensional vectors into compact integer sequences, known as quantization codes - -a classical and versatile compression method. Subsequently, we introduce DCQ, which builds upon the differential concept to perform lossless compression on quantization codes. DCQ organizes quantization codes into a tree structure and constructs a hierarchy of trees by analyzing the dissimilarity between two quantization codes. To minimize the impact on query performance, we have developed an adaptive reconstruction algorithm that partitions and reconstructs the original tree structure. This algorithm effectively balances the workload for searching each sub-tree, optimizing the compression-performance trade-off. Finally, we adopt a storage format based on multiple subtrees for rapid searching, thereby enabling differential storage to facilitate efficient queries. Extensive experiments on various large-scale real-world datasets show that DCQ achieves a compression ratio of up to 2.5 on the quantization codes and achieves > 50× performance improvement compared to the state-of-the-art general-purpose lossless compression techniques. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Trees (mathematics)

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：