检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Big Data and Smart computing, BigComp 2025

作者： Lee, Young-Jun Choi, Ho-Jin Korea Advanced Institute of Science and Technology School of Computing Daejeon Korea Republic of

Recently, many vision-and-language models have demonstrated remarkable performance in various multimodal tasks using a zero-shot approach. However, they lack spatial reasoning abilities, particularly in understanding visuo-spatial information from another's perspective, a skill known as visual perspective taking. In this paper, we investigate whether vision-and-language models can develop visual perspective-taking abilities in a zero-shot manner. Through a simple experiment, we demonstrate that these models still struggle to see the world from another's viewpoint, suggesting that vision-and-language models are hindered by an egocentric bias. © 2025 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Graph-based 3D Collision-distance Estimation Network with Probabilistic Graph Rewiring

Graph-based 3D Collision-distance Estimation Network with Pr...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Minjae Song Yeseung Kim Min Jun Kim Daehyung Park School of Computing Korea Advanced Institute of Science and Technology Korea School of Electrical Engineering Korea Advanced Institute of Science and Technology Korea

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We aim to solve the problem of data-driven collision-distance estimation given 3-dimensional (3D) geometries. Conventional algorithms suffer from low accuracy due to their reliance on limited representations, such as point clouds. In contrast, our previous graph-based model, GraphDistNet, achieves high accuracy using edge information but incurs higher message-passing costs with growing graph size, limiting its applicability to 3D geometries. To overcome these challenges, we propose GDN-R, a novel 3D graph-based estimation network. GDN-R employs a layer-wise probabilistic graph-rewiring algorithm leveraging the differentiable Gumbel-top-K relaxation. Our method accurately infers minimum distances through iterative graph rewiring and updating relevant embeddings. The probabilistic rewiring enables fast and robust embedding with respect to unforeseen categories of geometries. Through 41, 412 random benchmark tasks with 150 pairs of 3D objects, we show GDN-R outperforms state-of-the-art baseline methods in terms of accuracy and generalizability. We also show that the proposed rewiring improves the update performance reducing the size of the estimation model. We finally show its batch prediction and auto-differentiation capabilities for trajectory optimization in both simulated and real-world scenarios.

关键词： Geometry Solid modeling Three-dimensional displays Accuracy Estimation Benchmark testing Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction to Evaluate the Quality of Data Using Machine Learning Technique

Feature Extraction to Evaluate the Quality of Data Using Mac...

引用

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： R Pratheesh V. Divya School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Data quality analysis is a crucial step in ensuring the reliability and accuracy of data used in machine learning models. The proposed approach utilized with machine learning algorithms to identify outliers in the data. Outliers can indicate errors are anomalies that might affect the quality of the dataset. Data Profiling is used to identify patterns and distributions. Missing Data Imputation predict the missing values. Data Validation and Cleansing, Data Duplication Detection, Inconsistency Detection are considered as the primary analysis to be done. The feature extraction process read the sample test dataset, pre-process the dataset by cleaning the data for data duplication, inconsistency through dynamic algorithms principal component analysis (PCA), Linear Discriminant Analysis (LDA) and independent component analysis (ICA) is considered here. The proposed feature extraction data is further opted for pattern validation through isolated forest algorithm. The performance of the system is evaluated using accuracy, precision, and Recall. The LDA model outperforms with accuracy of 99% for the given testset.

关键词： Machine learning algorithms Heuristic algorithms System performance Machine learning Independent component analysis Feature extraction Cleaning

来源：评论

学校读者我要写书评

暂无评论

Degenerate polarization entangled photon source based on a single Ti-diffusion lithium niobate waveguide in a polarization Sagnac interferometer

引用

Chinese Physics B 2023年第8期32卷 69-73页

作者：孙宇孙昌伟周唯杨然端家晨龚彦晓徐平祝世宁 National Laboratory of Solid State Microstructures and School of Physics Nanjing UniversityNanjing 210093China NanZhi Institude of Advanced Optoelectronic Integration Nanjing 210018China Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China

Combining a Ti-diffusion periodically poled lithium niobate(PPLN)waveguide with a Sagnac interferometer,two opposite directions type-II spontaneous parametric down conversions(SPDC)occur coherently and yield a high brightness,high stability polarization entanglement *** source produces degenerate photon pairs at 1540.4 nm with a brightness of B=(1.36±0.03)×10^(6) pairs/(s·nm·m W).We perform quantum state tomography to reconstruct the density matrix of the output state and obtain a fidelity of F=0.983±*** high brightness and phase stability of our waveguide source enable a wide range of quantum information experiments operating at a low pump power as well as hold the advantage in mass production which can promote the practical applications of quantum technologies.

关键词： polarization entanglement source Sagnac interferometer quantum information lithium niobate waveguide

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Photovoltaic Solar Panel Monitoring System Based on Internet of Things

An Implementation of Photovoltaic Solar Panel Monitoring Sys...

引用

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： J. Saranya V. Divya School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

The Internet of Things (IoT) is a contemporary technology that enhances user experience and adds intelligence to objects. Numerous applications have already embraced the Internet of Things. The Internet of Things (IoT) has greatly simplified and increased the accessibility of our lives. Society will be better equipped to safeguard future generations by reducing greenhouse gas emissions and ozone depletion as long as everyone uses renewable energy. These PV technologies are growing in popularity because they are so widely available, reasonably priced, and easy to install and maintain. Monitoring is required to determine the current condition of each solar photovoltaic cell in a solar panel. This monitoring is necessary to detect any defects in the solar cell and implement repair actions in addition to guaranteeing that the solar panel continues to function properly. In this study, an Internet of Things-based solar panel monitoring system is implemented, and the MPPT algorithm is used to track maximum power.

关键词： Wireless communication Maximum power point trackers Renewable energy sources Photovoltaic cells Energy efficiency User experience Internet of Things

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

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

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding

arXiv

引用

arXiv 2025年

作者： Cho, Sukmin Choi, Sangjin Hwang, Taeho Seo, Jeongyeon Jeong, Soyeong Lee, Huije Song, Hoyun Park, Jong C. Kwon, Youngjin School of Computing Korea Advanced Institute of Science and Technology Korea Republic of Graduate School of AI Korea Advanced Institute of Science and Technology Korea Republic of

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as LLMs have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for improving inference speed by drafting and verifying tokens, thereby generating multiple tokens in a single forward pass. However, current drafting strategies usually require significant fine-tuning or have inconsistent performance across tasks. To address these challenges, we propose Hierarchy Drafting (HD)1, a novel lossless drafting approach that organizes various token sources into multiple databases in a hierarchical framework based on temporal locality. In the drafting step, HD sequentially accesses multiple databases to obtain draft tokens from the highest to the lowest locality, ensuring consistent acceleration across diverse tasks and minimizing drafting latency. Our experiments on Spec-Bench using LLMs with 7B and 13B parameters demonstrate that HD outperforms existing lossless drafting methods, achieving robust inference speedups across model sizes, tasks, and temperatures. © 2025, CC BY-NC-SA.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Comparison of self-supervised learning methods for optical coherence tomography image classification 24

Comparison of self-supervised learning methods for optical c...

引用

8th International Conference on Medical and Health Informatics, ICMHI 2024

作者： Shim, Sungho Yang, Hyun-Lim Kim, Min-Soo Electrical Engineering and Computer Science Daegu Gyeongbuk Institute of Science and Technology Daegu Korea Republic of Office of Hospital Information Seoul National University Hospital Seoul Korea Republic of School of Computing Korea Advanced Institute of Science and Technology Daejeon Korea Republic of

ISBN: (纸本)9798400716874

Self-supervised learning enables deep learning algorithms to achieve high performance even with limited labeled data. Numerous self-supervised learning methods have been proposed, and several medical artificial intelligence studies have confirmed the effectiveness of this technique in enhancing model performance. Nonetheless, only a few studies have investigated which self-supervised learning methods are appropriate for medical images. In this study, a comparative analysis to determine the most suitable self-supervised learning methods for developing medical artificial intelligence models using optical coherence tomography images. Four self-supervised learning methods were tested, and models were developed and validated using two publicly available optical coherence tomography datasets. The reliability of the model output was assessed through Gradient-weighted Class Activation Mapping analysis. As a result, using contrastive learning-based self-supervised learning methods, better performance was observed compared to other models, resulting in 99.90% and 99.05% accuracy for the two public optical coherence tomography datasets, which represents a 0.8% and 2.86% improvement over conventional supervised learning training. In addition, we confirmed that the contrastive learning-based model can more reliably localize disease lesions in the Gradient-weighted Class Activation Mapping analysis. © 2024 Copyright held by the owner/author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of multiplexer combination in rtl logic synthesis

Optimization of multiplexer combination in rtl logic synthes...

引用

2023 International Symposium of Electronics Design Automation, ISEDA 2023

作者： Wang, Zicheng You, Hailong Wang, Jie Liu, Meihua Su, Yu Zhang, Yong School of Microelectronics Xidian University Xian China Institute of Advanced Computing and Digital Engineering Shenzhen Institude of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen GWX Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350304510

The paper presents an optimizable multiplexer combination in logic synthesis of RTL level circuits. There are often some redundant multiplexers in the circuit, the deletion or optimization of these multiplexers does not affect the design behavior of circuits. Therefore, we propose a special multiplexer combination. It can be optimized on the premise that the logic function of the circuit remains unchanged, and it can also be merged with other traditional optimizable multiplexers to further optimize the circuit. In the paper, we use examples to optimize and verify, the results show that the optimizable combination can effectively reduce the number of multiplexers, The results show that the optimizable combination can significantly reduce the number of multiplexer elements, and appears more frequently and probably in the circuit. The optimizable combination is feasible and practical in the logic synthesis of circuits, which can effectively reduce the number of elements and design scale of the circuit. © 2023 IEEE.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Unmasking Malware with MDCNN: A New Era of Image-Based Detection

Unmasking Malware with MDCNN: A New Era of Image-Based Detec...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： Gomathy M A. Vidhya School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai Tamilnadu Department of Information Technology School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai Tamilnadu.

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Cybercrime has been a worldwide issue since the internet's inception. The various online crimes that take place have an impact on the general public. The various forms of cybercrime committed online and around the world are always evolving due to the development of the internet. In the current digital age, when malware diversity and volume are increasing rapidly, new methods must be used to identify malware more quickly and accurately. Malware, which includes worms, trojans, spyware, and adware, can have serious repercussions, including financial losses, data breaches, and the interruption of essential services. Manual heuristic inspection in malware analysis is neither efficient nor effective in keeping up with the rapid spread of malware or in analyzing new infections. Deep learning enhances automatic malware variant detection and classification as it provides better categorization by building neural networks with more potentially different layers. They have been applied to automate investigations using static and dynamic analysis, where malware with comparable behaviors is grouped and unidentified malware is categorized into families according to how close it is to the other malware. To analyze malware in a file, certain features from the PE header format may mislead the model into classifying malware as benign. However, when the same file is represented as an image, the distinct patterns in different sections make it easier to categorize the file as either malware or benign. Furthermore, as new malware variants emerge daily, the complexity of these patterns increases, making it difficult for traditional models to analyze them effectively. Our research proposes a deep learning model, MDCNN, to address the challenges faced by existing models in accurately categorizing executable files represented as images into malware or benign. This research study extracts various feature sets from malware image files, including patterns, sizes, and textures, we utilized a novel

关键词： Deep learning Analytical models Accuracy Transforms Feature extraction Malware Convolutional neural networks Trojan horses Computer crime Spyware

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：