检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kennington, Casey Lison, Pierre Schlangen, David DEPARTMENT OF COMPUTER SCIENCE BOISE STATE UNIVERSITY United States NORWEGIAN COMPUTING CENTER Norway COMPUTATIONAL LINGUISTICS UNIVERSITY OF POTSDAM Germany

Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their processing is inherently monotonic and thus lack the ability to revise their interpretations or output in light of newer observations. This monotonicity has important implications for the development of dialogue systems for human–robot interaction. In this paper, we review the literature on interactive systems that operate incrementally (i.e., at the word level or below it). We motivate the need for incremental systems, survey incremental modeling of important aspects of dialogue like speech recognition and language generation. Primary focus is on the part of the system that makes decisions, known as the dialogue manager. We find that there is very little research on incremental dialogue management, offer some requirements for practical incremental dialogue management, and the implications of incremental dialogue for embodied, robotic platforms in the age of large language models. © 2025, CC BY.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

End-to-end Optimized Lossy Compression for Neural-morphic Spiking Camera Captured Data

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Feng, Kexiang Jia, Chuanmin Pan, Jingshan Ma, Siwei Gao, Wen Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Peking University National Engineering Research Center of Visual Technology Beijing100871 China Peking University Wangxuan Institute of Computer Technology Beijing100080 China Shandong Computer Science Center National Supercomputer in Jinan Jinan250014 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we propose a novel Reconstruction-based Contextual Spike Compression (RCSC) framework, which contains scene reconstruction, contextual image compression and spike generation. To our knowledge, it is the first learning-based model for efficient and robust spike stream compression with informative fidelity. Extensive experimental results show that our model outperforms the state-of-the-art conventional codec VVC intra by 6.14% and surpasses the state-of-the-art learned codec by 2.53% in BD-rate reduction, establishing a strong baseline for spike compression. © 1991-2012 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

AutoQ 2.0: From Verification of Quantum Circuits to Verification of Quantum Programs 31th

AutoQ 2.0: From Verification of Quantum Circuits to Verific...

引用

31st International Conference on Tools and Algorithms for the Construction and Analysis of Systems, TACAS 2025, which was held as part of the International Joint Conferences on Theory and Practice of Software, ETAPS 2025

作者： Chen, Yu-Fang Chung, Kai-Min Hsieh, Min-Hsiu Huang, Wei-Jia Lengál, Ondřej Lin, Jyun-Ao Tsai, Wei-Lun Institute of Information Science Academia Sinica Taipei Taiwan Hon Hai Quantum Computing Research Center Taipei Taiwan Faculty of Information Technology Brno University of Technology Brno Czech Republic Innovation Frontier Institute of Research for Science and Technology & Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9783031906596

We present a verifier of quantum programs called AutoQ 2.0. Quantum programs extend quantum circuits (the domain of AutoQ 1.0) by classical control flow constructs, which enable users to describe advanced quantum algorithms in a formal and precise manner. The extension is highly non-trivial, as we needed to tackle both theoretical challenges (such as the treatment of measurement, the normalization problem, and lifting techniques for verification of classical programs with loops to the quantum world), and engineering issues (such as extending the input format with a support for specifying loop invariants). We have successfully used AutoQ 2.0 to verify two types of advanced quantum programs that cannot be expressed using only quantum circuits: the repeat-until-success (RUS) algorithm and the weak-measurement-based version of Grover’s search algorithm. AutoQ 2.0 can efficiently verify all our benchmarks: all RUS algorithms were verified instantly and, for the weak-measurement-based version of Grover’s search, we were able to handle the case of 100 qubits in ∼20 minutes. © The Author(s) 2025.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs 24

Testing GPU Numerics: Finding Numerical Differences Between ...

引用

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

作者： Anwar Hossain Zahid Ignacio Laguna Wei Le Department of Computer Science Iowa State University Ames IA Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA

ISBN: (纸本)9798350355543

As scientific codes are ported between GPU platforms, continuous testing is required to ensure numerical robustness and identify potential numerical differences between platforms. Compiler-induced numerical differences can occur when a program is compiled and run on different GPUs and compilers, and the numerical outcomes are different for the same input. We present a study of compiler-induced numerical differences between NVIDIA and AMD GPUs, two widely used GPUs in HPC clusters. Our approach uses a random program generator (Varity) to generate thousands of short numerical tests in CUDA and HIP, and their inputs; then, we use differential testing to check if the program produced a numerical inconsistency when run on NVIDIA and AMD GPUs, using the same compiler optimization level. We also use the AMD's HIPIFY tool to convert CUDA tests into HIP tests and test if there are numerical inconsistencies induced by HIPIFY. In our study, we generated more than 600,000 tests and found subtle numerical differences occurring between the two classes of GPUs. We found that some of the differences come from (1) math library calls, (2) differences in floating-point precision (FP64 versus FP32), and (3) converting code to HIP with HIPIFY.

关键词： CUDA

来源：评论

学校读者我要写书评

暂无评论

The Minimal Search Space for Conditional Causal Bandits

arXiv

引用

arXiv 2025年

作者： Simoes, Francisco N.F.Q. Feigenbaum, Itai Dastani, Mehdi van Omen, Thijs Department of Information and Computing Sciences Utrecht University Netherlands Department of Computer Science Lehman College Graduate Center City University of New York United States

Causal knowledge can be used to support decision-making problems. This has been recognized in the causal bandits literature, where a causal (multi-armed) bandit is characterized by a causal graphical model and a target variable. The arms are then interventions on the causal model, and rewards are samples of the target variable. Causal bandits were originally studied with a focus on hard interventions. We focus instead on cases where the arms are conditional interventions, which more accurately model many real-world decision-making problems by allowing the value of the intervened variable to be chosen based on the observed values of other variables. This paper presents a graphical characterization of the minimal set of nodes guaranteed to contain the optimal conditional intervention, which maximizes the expected reward. We then propose an efficient algorithm with a time complexity of O(|V |+ |E|) to identify this minimal set of nodes. We prove that the graphical characterization and the proposed algorithm are correct. Finally, we empirically demonstrate that our algorithm significantly prunes the search space and substantially accelerates convergence rates when integrated into standard multi-armed bandit algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Detection of APT Vector Lateral Movement in Organizational Networks Using Lightweight Machine Learning

引用

computers, Materials & Continua 2025年第4期83卷 281-308页

作者： Mathew Nicho Oluwasegun Adelaiye Christopher D.McDermott Shini Girija Research and Innovation Center Rabdan AcademyAbudhabiP.O.Box 114646United Arab Emirates UQ Cyber Research Centre The University of QueenslandBrisbaneQLD 4027Australia Department of Computer Science Bingham UniversityAbuja961105Nigeria School of Computing Robert Gordon UniversityAberdeenAB107QBUK College of Technological Innovation Zayed UniversityDubaiP.O.Box 144534United Arab Emirates

The successful penetration of government,corporate,and organizational IT systems by state and non-state actors deploying APT vectors continues at an alarming *** Persistent Threat(APT)attacks continue to pose significant challenges for organizations despite technological advancements in artificial intelligence(AI)-based defense *** AI has enhanced organizational capabilities for deterrence,detection,and mitigation of APTs,the global escalation in reported incidents,particularly those successfully penetrating critical government infrastructure has heightened concerns among information technology(IT)security administrators and *** review has identified the stealthy lateral movement(LM)of malware within the initially infected local area network(LAN)as a significant ***,current literature has yet to propose a viable approach for resource-efficient,real-time detection of APT malware lateral movement within the initially compromised LAN following perimeter *** have suggested the nature of the dataset,optimal feature selection,and the choice of machine learning(ML)techniques as critical factors for ***,the objective of the research described here was to successfully demonstrate a simplified lightweight ML method for detecting the LM of APT *** the nearest detection rate achieved in the LM domain within LAN was 99.89%,as reported in relevant studies,our approach surpassed it,with a detection rate of 99.95%for the modified random forest(RF)classifier for dataset ***,our approach achieved a perfect 100%detection rate for the decision tree(DT)and RF classifiers with dataset 2,a milestone not previously reached in studies within this domain involving two distinct *** the ML life cycle methodology,we deployed K-nearest neighbor(KNN),support vector machine(SVM),DT,and RF on three relevant datasets to detect the LM of APTs at the affected LAN prior to data exfiltrat

关键词： Intrusion detection lateral movement machine learning advanced persistent threats

来源：评论

学校读者我要写书评

暂无评论

Accurately Estimating Unreported Infections using Information Theory

arXiv

引用

arXiv 2025年

作者： Cui, Jiaming Adhikari, Bijaya Haddadan, Arash Ul Haque, A.S.M. Ahsan Vreeken, Jilles Vullikanti, Anil Prakash, B. Aditya College of Computing Georgia Institute of Technology United States Department of Computer Science University of Virginia United States Department of Computer Science Virginia Tech United States Department of Computer Science The University of Iowa United States Amazon United States CISPA Helmholtz Center for Information Security Germany

One of the most significant challenges in combating against the spread of infectious diseases was the difficulty in estimating the true magnitude of infections. Unreported infections could drive up disease spread, making it very hard to accurately estimate the infectivity of the pathogen, therewith hampering our ability to react effectively. Despite the use of surveillance-based methods such as serological studies, identifying the true magnitude is still challenging. This paper proposes an information theoretic approach for accurately estimating the number of total infections. Our approach is built on top of Ordinary Differential Equations (ODE) based models, which are commonly used in epidemiology and for estimating such infections. We show how we can help such models to better compute the number of total infections and identify the parametrization by which we need the fewest bits to describe the observed dynamics of reported infections. Our experiments on COVID-19 spread show that our approach leads to not only substantially better estimates of the number of total infections but also better forecasts of infections than standard model calibration based methods. We additionally show how our learned parametrization helps in modeling more accurate what-if scenarios with non-pharmaceutical interventions. Our approach provides a general method for improving epidemic modeling which is applicable broadly. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

APP: Enabling Soft Real-Time Execution on Densely-Populated Hybrid Memory System 23

APP: Enabling Soft Real-Time Execution on Densely-Populated ...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Zheng-Wei Wu Yun-Chih Chen Yuan-Hao Chang Tei-Wei Kuo Department of Computer Science and Information Engineering National Taiwan University Institute of Information Science Academia Sinica Taiwan Department of Computer Science and Information Engineering National Taiwan University and Mohamed bin Zayed University of Artificial Intelligence Department of Computer Science and NTU High Performance and Scientific Computing Center National Taiwan University

ISBN: (纸本)9798350323481

Memory swapping was considered slow and evil, but swapping to Ultra Low-Latency storage like Optane has become a promising solution to save power and cost, helping densely-populated edge server to overcome its DRAM capacity bottleneck. However, the lack of integration between CPU scheduling and memory paging causes soft real-time tasks running on edge servers to miss deadlines under heavy memory multiplexing. We propose APP (Adaptive Page Pinning), lightweight protection of working set memory to ensure meeting soft real-time task deadlines without starving other non-real-time tasks. Experiments show that APP alleviates thrashing in memory-intensive tasks and upholds soft real-time task deadlines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields

arXiv

引用

arXiv 2025年

作者： Luo, Ziyuan Rocha, Anderson Shi, Boxin Guo, Qing Li, Haoliang Wan, Renjie Department of Computer Science Hong Kong Baptist University Hong Kong Institute of Computing University of Campinas Brazil State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China A*STAR Singapore Department of Electrical Engineering City University of Hong Kong Hong Kong

Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some approaches have been proposed to embed digital watermarks into NeRF, they often neglect essential model-level considerations and incur substantial time overheads, resulting in reduced imperceptibility and robustness, along with user inconvenience. In this paper, we extend the previous criteria for image watermarking to the model level and propose NeRF Signature, a novel watermarking method for NeRF. We employ a Codebook-aided Signature Embedding (CSE) that does not alter the model structure, thereby maintaining imperceptibility and enhancing robustness at the model level. Furthermore, after optimization, any desired signatures can be embedded through the CSE, and no fine-tuning is required when NeRF owners want to use new binary signatures. Then, we introduce a joint pose-patch encryption watermarking strategy to hide signatures into patches rendered from a specific viewpoint for higher robustness. In addition, we explore a Complexity-Aware Key Selection (CAKS) scheme to embed signatures in high visual complexity patches to enhance imperceptibility. The experimental results demonstrate that our method outperforms other baseline methods in terms of imperceptibility and robustness. The source code is available at: https://***/luo-ziyuan/NeRF_Signature. Copyright © 2025, The Authors. All rights reserved.

关键词： Image watermarking

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：