检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yunhui Liu Huaisong Zhang Xinyi Gao Liuye Guo Zhen Tao Tieke He State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Link Prediction (LP) is a crucial problem in graph-structured data. Graph Neural Networks (GNNs) have gained prominence in LP, with Graph AutoEncoders (GAEs) being a notable representation. However, our empirical findings reveal that GAEs’ LP performance suffers heavily from the long-tailed node degree distribution, i.e., low-degree nodes tend to exhibit inferior LP performance compared to high-degree nodes. What causes this degree-related bias, and how can it be mitigated? In this study, we demonstrate that the norm of node embeddings learned by GAEs exhibits variation among nodes with different degrees, underscoring its central significance in influencing the final performance of LP. Specifically, embeddings with larger norms tend to guide the decoder towards predicting higher scores for positive links and lower scores for negative links, thereby contributing to superior performance. This observation motivates us to improve GAEs’ LP performance on low-degree nodes by increasing their embedding norms, which can be implemented simply yet effectively by introducing additional self-loops into the training objective for low-degree nodes. This norm augmentation strategy can be seamlessly integrated into existing GAE methods with light computational cost. Extensive experiments on various datasets and GAE methods show the superior performance of norm-augmented GAEs.

关键词： Training Bridges Heavily-tailed distribution Autoencoders Signal processing Graph neural networks Acoustics Decoding Computational efficiency Speech processing

来源：评论

学校读者我要写书评

暂无评论

Online Optimization of Offloading Video Analytics Tasks to Multiple Edges for Accuracy Maximization

Online Optimization of Offloading Video Analytics Tasks to M...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yu Liang Sheng Zhang Jie Wu School of Computer and Electronic Information and the School of Artificial Intelligence Nanjing Normal University State Key Laboratory for Novel Software Technology Nanjing University Center for Networked Computing Temple University US

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Real-time video analytics (VA) presents challenges due to its computational intensity and latency sensitivity, especially when processed on mobile devices with limited local resources. We propose to offload VA tasks to edge servers with diverse computational capabilities. We present a "detect + track" approach with on-device object tracking and edge-assisted object detection. We formulate a long-term nonlinear integer programming to maximize the overall accuracy within detection frequency and latency constraints. We then design a queue-based online optimization algorithm to solve it: relax the original problem from the integer domain to the real domain, then employ a queue-based adaptation and randomized rounding strategy. Via rigorous proof, both dynamic regret regarding detection accuracy and the real-time requirement are ensured. Evaluation results also demonstrate the effectiveness of our approach.

关键词： Accuracy Image edge detection Visual analytics Signal processing algorithms Streaming media Signal processing Real-time systems Servers Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

DRPTM: A Decoupled Read-Efficient High-Scalable Persistent Transactional Memory 23

DRPTM: A Decoupled Read-Efficient High-Scalable Persistent T...

引用

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

作者： Wenkai Liang Hao Hu Xiangyu Zou Wen Xia Yanqi Pan School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China and Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies

ISBN: (纸本)9798350323481

Persistent transactional memory (PTM) exploits transactions to provide an easy crash-consistent interface for persistent memory (PM). However, because of the substantial reader-side overhead brought on by the low bandwidth and long persistence latency of PM, present PTM research cannot scale effectively. This paper proposes a highly scalable PTM system, DRPTM, which allows nearly non-overhead reads without lowering the isolation level. DRPTM decouples persistence latency from concurrency control and traces the read-only copy maintained in logs as a lightweight read set. The evaluation shows that DRPTM significantly outperforms the state-of-the-art PTM systems for various workloads and achieves near-linear scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining

arXiv

引用

arXiv 2025年

作者： Wang, Haoran Huai, Lian Li, Wenbin Qi, Lei Jiang, Xingqun Shi, Yinghuan National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing China National Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University Nanjing Drum Tower Hospital Jiangsu Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China Lab School of Computer Science and Engineering Southeast University Jiangsu Nanjing China BOE Technology Group Co. Ltd. Beijing China

We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus on training an adaptor for fine-tuning a large amount of pixel-wise annotated medical images following a fully supervised manner. In this paper, to reduce the labeling cost, we investigate a novel weakly-supervised SAM-based segmentation model, namely WeakMedSAM. Specifically, our proposed WeakMedSAM contains two modules: 1) to mitigate severe co-occurrence in medical images, a sub-class exploration module is introduced to learn accurate feature representations. 2) to improve the quality of the class activation maps, our prompt affinity mining module utilizes the prompt capability of SAM to obtain an affinity map for random-walk refinement. Our method can be applied to any SAM-like backbone, and we conduct experiments with SAMUS and EfficientSAM. The experimental results on three popularly-used benchmark datasets, i.e., BraTS 2019, AbdomenCT-1K, and MSD Cardiac dataset, show the promising results of our proposed WeakMedSAM. Our code is available at https://***/wanghr64/WeakMedSAM. Copyright © 2025, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology SydneyNSW2007 Australia Institute of Software Chinese Academy of Sciences Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 1982-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Towards an effective method of ReDoS detection for non-backtracking engines 24

Towards an effective method of ReDoS detection for non-backt...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Weihao Su Hong Huang Rongchen Li Haiming Chen Tingjian Ge Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Miner School of Computer & Information Sciences University of Massachusetts Lowell

ISBN: (纸本)9781939133441

Regular expressions (regexes) are a fundamental concept across the fields of computer science. However, they can also induce the Regular expression Denial of Service (Re-DoS) attacks, which are a class of denial of service attacks, caused by super-linear worst-case matching time. Due to the severity and prevalence of ReDoS attacks, the detection of ReDoS-vulnerable regexes in software is thus vital. Although various ReDoS detection approaches have been proposed, these methods have focused mainly on backtracking regex engines, leaving the problem of ReDoS vulnerability detection on non-backtracking regex engines largely *** address the above challenges, in this paper, we first systematically analyze the major causes that could contribute to ReDoS vulnerabilities on non-backtracking regex engines. We then propose a novel type of ReDoS attack strings that builds on the concept of simple strings. Next we propose EVILSTRGEN, a tool for generating attack strings for ReDoS-vulnerable regexes on non-backtracking engines. It is based on a novel incremental determinisation algorithm with heuristic strategies to lazily find the k-simple strings without explicit construction of finite automata. We evaluate EVILSTRGEN against six state-of-the-art approaches on a broad range of publicly available datasets containing 736,535 unique regexes. The results illustrate the significant efficacy of our tool. We also apply our tool to 85 intensively-tested projects, and have identified 34 unrevealed ReDoS vulnerabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CODESWIFT: Accelerating LLM Inference for Efficient Code Generation

arXiv

引用

arXiv 2025年

作者： Zhao, Qianhui Zhang, Li Liu, Fang Lian, Xiaoli Meng, Qiaoyuanhe Jiao, Ziqian Zhou, Zetong Zhang, Borui Guo, Runlin Li, Jia School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Key Lab of High Confidence Software Technology Peking University China

Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CODESWIFT, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CODESWIFT constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CODESWIFT reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CODESWIFT can reach up to 2.53× and 2.54× speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. Our code and data are available at https://***/r/CodeSwift. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Visual Acuity Consistent Foveated Rendering towards Retinal Resolution

引用

IEEE Transactions on Visualization and computer Graphics 2025年 PP卷 PP页

作者： Zhang, Zhi Gai, Meng Li, Sheng Peking University School of Software and Microelectronics China Peking University School of Computer Science China National Key Laboratory of Intelligent Parallel Technology China

Prior foveated rendering methods often suffer from a limitation where the shading load escalates with increasing display resolution, leading to decreased efficiency, particularly when dealing with retinal-level resolutions. To tackle this challenge, we begin with the essence of the human visual system (HVS) perception and present visual acuity-consistent foveated rendering (VaFR), aiming to achieve exceptional rendering performance at retinal-level resolutions. Specifically, we propose a method with a novel log-polar mapping function derived from the human visual acuity model, which accommodates the natural bandwidth of the visual system. This mapping function and its associated shading rate guarantee a consistent output of rendering information, regardless of variations in the display resolution of the VR HMD. Consequently, our VaFR outperforms alternative methods, improving rendering speed while preserving perceptual visual quality, particularly when operating at retinal resolutions. We validate our approach using both the rasterization and ray-casting rendering pipelines. We also validate our approach using different binocular rendering strategies for HMD devices. In diverse testing scenarios, our approach delivers better perceptual visual quality than prior foveated rendering while achieving an impressive speedup of 6.5×-9.29× for deferred rendering of 3D scenarios and an even more powerful speedup of 10.4×-16.4× for ray-casting at retinal resolution. Additionally, our approach significantly enhances the rendering performance of binocular 8K path tracing, achieving smooth frame rates. © 1995-2012 IEEE.

关键词： Binoculars

来源：评论

学校读者我要写书评

暂无评论

Revealing atomic strengthening mechanism in CoNiV medium-entropy alloy via machine learning-guided simulations

引用

Journal of Materials science and technology 2025年 238卷 66-77页

作者： Li, Wenyue Liu, Xiongjun Liu, Leqing Du, Qing Lin, Deye Chen, Xin He, Dong Wang, Shudao Wu, Yuan Wang, Hui Jiang, Suihe Zhang, Xiaobin Lu, Zhaoping Beijing Advanced Innovation Center for Materials Genome Engineering State Key Laboratory for Advanced Metals and Materials University of Science and Technology Beijing Beijing100083 China School of Intelligent Manufacturing and Mechanical Engineering Hunan Institute of Technology Hengyang421002 China School of Materials Science and Engineering Ocean University of China Qingdao266100 China CAEP Software Center for High Performance Numerical Simulation Beijing100088 China Institute of Applied Physics and Computational Mathematics Beijing100094 China School of Materials Science and Engineering Dalian University of Technology Dalian116024 China

High/medium entropy alloys (H/MEAs) have shown unique strengthening behavior and mechanical properties because of the presence of massive local chemical orderings. Nevertheless, dynamic interactions between chemical short-range orders (CSROs) and dislocations, and the underlying atomic strengthening mechanism remain elusive. In this work, we first developed a novel machine learning-embedded atom method (ML-EAM) potential of the CoNiV system, trained on a comprehensive first-principles dataset, which enables accurate and efficient modeling of CSRO formation and dislocation dynamics. Then, we investigated the strengthening mechanisms of CSROs in CoNiV MEA through machine learning-augmented molecular dynamics (MD) simulations. Hybrid MD/Monte Carlo simulations reveal that CSRO domains possess an L12 (NiCo)3 V structure, whose size increases with lowering annealing temperatures. These domains significantly enhance strength by impeding dislocation motion through complex energy pathways, increasing depinning forces, and reducing mobility. Moreover, the MD simulations combined with theoretical analysis elucidate the competition between CSRO-assisted strengthening (via antiphase boundary formation) and solid solution weakening (via reduced atomic misfit volume). Phonon-drag effects are also amplified by CSROs, further resisting dislocation glide. Our results demonstrate that L12-CSROs strengthen CoNiV MEA primarily through antiphase boundary and phonon-drag contributions, providing new insights for designing high-performance multi-principal-element alloys via tailoring CSROs. © 2025

关键词： Turing machines

来源：评论

学校读者我要写书评

暂无评论

EQUIVARIANT MASKED POSITION PREDICTION FOR EFFICIENT MOLECULAR REPRESENTATION

arXiv

引用

arXiv 2025年

作者： An, Junyi Qu, Chao Shi, Yunfei Liu, Xinhao Tang, Qianwei Cao, Fenglei Qi, Yuan Shanghai Academy of Artificial Intelligence for Science China Co. Ltd China School of Computer Science Fudan University China State Key Laboratory for Novel Software Technology Nanjing University China Institute Fudan University China

Graph neural networks (GNNs) have shown considerable promise in computational chemistry. However, the limited availability of molecular data raises concerns regarding GNNs’ ability to effectively capture the fundamental principles of physics and chemistry, which constrains their generalization capabilities. To address this challenge, we introduce a novel self-supervised approach termed Equivariant Masked Position Prediction (EMPP), grounded in intramolecular potential and force theory. Unlike conventional attribute masking techniques, EMPP formulates a nuanced position prediction task that is more well-defined and enhances the learning of quantum mechanical features. EMPP also bypasses the approximation of the Gaussian mixture distribution commonly used in denoising methods, allowing for more accurate acquisition of physical properties. Experimental results indicate that EMPP significantly enhances performance of advanced molecular architectures, surpassing state-of-the-art self-supervised approaches. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

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：