检索结果-内蒙古大学图书馆

Testing the Unknown: A Framework for OpenMP Testing via Random Program Generation 24

Testing the Unknown: A Framework for OpenMP Testing via Rand...

Proceedings of the SC '24 Workshops of the International Conference on High Performance computing, Network, Storage, and Analysis

作者： Ignacio Laguna Patrick Chapman Konstantinos Parasyris Giorgis Georgakoudis Cindy Rubio-González Center for Applied Scientific Computing Lawrence Livermore National Laboratory Department of Computer Science University of California Davis

ISBN: (纸本)9798350355543

We present a randomized differential testing approach to test OpenMP implementations. In contrast to previous work that manually creates dozens of verification and validation tests, our approach is able to randomly generate thousands of tests, exposing OpenMP implementations to a wide range of program behaviors. We represent the space of possible random OpenMP tests using a grammar and implement our method as an extension of the Varity program generator. By generating 1,800 OpenMP tests, we find various performance anomalies and correctness issues when we apply them to three OpenMP implementations: GCC, Clang, and Intel. We also present several case studies that analyze the anomalies and give more details about the classes of tests that our approach creates.

关键词： OpenMP

来源：评论

学校读者我要写书评

暂无评论

visual Augmentations for Ultrasound Assessment Training of Medical Students 25

Visual Augmentations for Ultrasound Assessment Training of M...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing Systems

作者： Helena Bøjer Djernæs Rune Møberg Jacobsen Simo Hosio Niels van Berkel Department of Computer Science Aalborg University Aalborg Denmark Center for Ubiquitous Computing University of Oulu Oulu Finland

来源：评论

学校读者我要写书评

暂无评论

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

arXiv

引用

arXiv 2025年

作者： Han, Feng Chen, Kai Gong, Chao Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model’s ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module’s outputs across different layers and timesteps, automatically balancing the erasure effects and model’s generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure (detecting only 34 nude parts), Cartoon Concept Removal (with an average LPIPSda of 0.428, 0.113 higher than SOTA at 0.315), and Artistic Style Erasure (with an average LPIPSda of 0.387, 0.088 higher than SOTA at 0.299), clearly outperforming alternative methods. Code is available at https://***/Maplebb/DuMo Copyright © 2025, The Author

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Distill & Contrast: A New Graph Self-Supervised Method With Approximating Nature Data Relationships

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3284-3297页

作者： He, Dongxiao Zhao, Jitao Guo, Rui Feng, Zhiyong Huo, Cuiying Jin, Di Pedrycz, Witold Zhang, Weixiong Tianjin University College of Intelligence and Computing Tianjin300350 China Department of Measurement and Control Systems Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Hong Kong Polytechnic University Department of Data Science and Ai Hong Kong

Contrastive Learning (CL) has emerged as a popular self-supervised representation learning paradigm that has been shown in many applications to perform similarly to traditional supervised learning methods. A key component of CL is mining the latent discriminative relationships between positive and negative samples and using them as self-supervised labels. We argue that this discriminative contrastive task is, in essence, similar to a classification task, and the "either positive or negative"hard label sampling strategies are arbitrary. To solve this problem, we explore ideas from data distillation, which considers probabilistic logit vectors as soft labels to transfer model knowledge. We attempt to abandon the classical hard sampling labels in CL and instead explore self-supervised soft labels. We adopt soft sampling labels that are extracted, without supervision, from the inherent relationships in data pairs to retain more information. We propose a new self-supervised graph learning method, Distill and Contrast (D&C), for learning representations that closely approximate natural data relationships. D&C extracts node similarities from the features and structures to derive soft sampling labels, which also eliminate noise in the data to increase robustness. Extensive experimental results on real-world datasets demonstrate the effectiveness of the proposed method. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

The HCI GenAI CO2ST Calculator: A Tool for Calculating the Carbon Footprint of Generative AI Use in Human-computer Interaction Research

arXiv

引用

arXiv 2025年

作者： Inie, Nanna Falk, Jeanette Selvan, Raghavendra IT University of Copenhagen Center for Computing Education Research Copenhagen Denmark Aalborg University Copenhagen Department of Computer Science Copenhagen Denmark University of Copenhagen Department of Computer Science Copenhagen Denmark

Increased usage of generative AI (GenAI) in Human-computer Interaction (HCI) research induces a climate impact from carbon emissions due to energy consumption of the hardware used to develop and run GenAI models and systems. The exact energy usage and and subsequent carbon emissions are difficult to estimate in HCI research because HCI researchers most often use cloud-based services where the hardware and its energy consumption are hidden from plain view. The HCI GenAI CO2ST Calculator is a tool designed specifically for the HCI research pipeline, to help researchers estimate the energy consumption and carbon footprint of using generative AI in their research, either a priori (allowing for mitigation strategies or experimental redesign) or post hoc (allowing for transparent documentation of carbon footprint in written reports of the research). © 2025, CC BY.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Rethinking Tokenized Graph Transformers for Node Classification

arXiv

引用

arXiv 2025年

作者： Chen, Jinsong Li, Chenyang Li, GaiChao Hopcroft, John E. He, Kun School of Computer Science and Technology Huazhong University of Science and Technology China Hopcroft Center on Computing Science Huazhong University of Science and Technology China Department of Computer Science Cornell University United States

Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token sequences, facilitating the node representation learning via Transformer. In this paper, we observe that the generations of token sequences in existing GTs only focus on the first-order neighbors on the constructed similarity graphs, which leads to the limited usage of nodes to generate diverse token sequences, further restricting the potential of tokenized GTs for node classification. To this end, we propose a new method termed SwapGT. SwapGT first introduces a novel token swapping operation based on the characteristics of token sequences that fully leverages the semantic relevance of nodes to generate more informative token sequences. Then, SwapGT leverages a Transformer-based backbone to learn node representations from the generated token sequences. Moreover, SwapGT develops a center alignment loss to constrain the representation learning from multiple token sequences, further enhancing the model performance. Extensive empirical results on various datasets showcase the superiority of SwapGT for node classification. © 2025, CC BY.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About It 25

How CO2STLY Is CHI? The Carbon Footprint of Generative AI in...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing Systems

作者： Nanna Inie Jeanette Falk Raghavendra Selvan Center for Computing Education Research (CCER) IT University of Copenhagen Copenhagen Denmark Department of Computer Science Aalborg University Copenhagen Denmark Department of Computer Science University of Copenhagen Copenhagen Denmark

来源：评论

学校读者我要写书评

暂无评论

Predictive modeling of MXene-based solar absorbers using a deep neural network

引用

Journal of the Optical Society of America B: Optical Physics 2025年第4期42卷 763-772页

作者： Waseer, Waleed Iqbal Baqir, Muhammad Abuzar Saqlain, Muhammad Mughal, Muhammad Junaid Khan, Shujaat School of Physics State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of China Chengdu China Department of Electrical Engineering COMSATS University Islamabad Sahiwal57000 Pakistan Department of Electrical and Computer Engineering COMSATS University Islamabad Islamabad45550 Pakistan Department of Computer Engineering College of Computing and Mathematics King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia

Nanophotonic structures, such as photonic crystals, plasmonic nanostructures, and metamaterials, present transformative potential in advancing optical devices through innovative design capabilities. Among these, metamaterials—specifically metal–insulator–metal (MIM)-based absorbers—stand out for their ability to achieve high electromagnetic wave absorption across designated frequencies, proving valuable in applications ranging from solar cells to sensors. This study focuses on designing a high-efficiency MXene–SiO2–silver MIM metasurface absorber, leveraging deep learning techniques to streamline and enhance the simulation process traditionally reliant on finite-difference time-domain (FDTD) or finite-element methods (FEMs). By utilizing a deformable convolutional neural network (CNN), the proposed model predicts absorption spectra from metasurface geometries with superior accuracy and reduced computational demand while achieving dynamic spatial transformation handling. The model’s accuracy is further elucidated through Gradient-weighted Class Activation Mapping (Grad-CAM), which provides insights into the absorber’s most influential regions, supporting targeted optimization for specific applications. This deep learning approach demonstrates significant advantages over conventional methods in efficiency and adaptability, advancing the development of high-performance nanophotonic devices. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Hashgraph consensus-based simultaneous, asynchronous and big-data supported blockchain mechanism for IT-OT enabled critical infrastructure sectors

引用

Journal of Ambient Intelligence and Humanized computing 2025年 1-13页

作者： Hasan, Mohammad Kamrul Ghazal, Taher M. Issa, Ghassan Islam, Shayla Ismail, Ahmad Fadzil Kabir, S. Rayhan Bangi43600 Malaysia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman11937 Jordan School of Computing Skyline University College University City Sharjah Skyline University College Sharjah1797 United Arab Emirates Institue of Computer Science and Digitial Innovation UCSI University Malaysia Kuala Lumpur56000 Malaysia Department of Electrical and Computer Engineering International Islamic University of Malaysia Kuala Lumpur53000 Malaysia

Critical Infrastructure (CI) refers to the essential areas made up of public, private, and business sectors for the security of a country's development, such as electricity, water, health, education, etc. where information technologies (ITs) and operational technologies (OTs) enable automation services of CI. Currently, blockchain is being experimented in various CI sectors and any CI sector accumulates the data of millions of people in a country or nation from which big data is being generated. Big data connections are seen with large-scale blockchain networks because as the size of the blockchain network increases, so does the amount of connected data. Typically, the blockchain does not support asynchronous and simultaneous processes that indicate multiple block compilation does not allow at the same time for the blockchain systems. That is why high energy consumption, high bandwidth dependency, long-time computation, high mining process, and system slowness issues are seen on large-scale blockchain networks where big data is also connected. However, Hashgraph is an alternative distributed ledger technology (DLT) to blockchain and is also considered a consensus method that supports Asynchronous Byzantine Fault Tolerance (ABFT) as well as simultaneous process. Moreover, Hashgraph does not need mining and network node verification processes which saves bandwidth. In this research, we proposed a Hashgraph-enabled blockchain model for reducing the above issues and illustrated the adoption of IT-enabled OT to support CI. In addition, this manuscript discusses how the proposed model can create positive impacts in CI areas by replacing traditional blockchain systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Deep Learning Approach for Predicting Job Queue Times in HPC Systems 24

A Hierarchical Deep Learning Approach for Predicting Job Que...

引用

Proceedings of the SC '24 Workshops of the International Conference on High Performance computing, Network, Storage, and Analysis

作者： Austin Lovell Philip Wisniewski Sarah Rodenbeck Ashish Department of Computer Science Purdue University Indiana USA Rosen Center for Advanced Computing Purdue University Indiana USA

ISBN: (纸本)9798350355543

Accurate wait-time prediction for HPC jobs contributes to a positive user experience but has historically been a challenging task. Previous models lack the accuracy needed for confident predictions, and many were developed before the rise of deep *** this work, we investigate and develop TROUT, a neural network-based model to accurately predict wait times for jobs submitted to the Anvil HPC cluster. Data was taken from the Slurm Workload Manager on the cluster and transformed before performing additional feature engineering from jobs' priorities, partitions, and states. We developed a hierarchical model that classifies job queue times into bins before applying regression, outperforming traditional methods. The model was then integrated into a CLI tool for queue time prediction. This study explores which queue time prediction methods are most applicable for modern HPC systems and shows that deep learning-based prediction models are viable solutions.

关键词： High-performance computing

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：