检索结果-内蒙古大学图书馆

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

arXiv

引用

arXiv 2025年

作者： Fang, Runnan Wang, Xiaobin Liang, Yuan Qiao, Shuofei Wu, Jialong Xi, Zekun Zhang, Ningyu Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Multitasking Algorithm for Efficient Multiobjective Recommendations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 518-532页

作者： Tian, Ye Ji, Luke Hu, Yiwei Ma, Haiping Wu, Le Zhang, Xingyi Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China Anhui University Institutes of Physical Science and Information Technology Hefei230601 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei230029 China

Represented by evolutionary algorithms and swarm intelligence algorithms, nature-inspired metaheuristics have been successfully applied to recommender systems and amply demonstrated effectiveness, in particular, for multiobjective recommendation. Owing to the population-based search paradigm, these algorithms can produce a number of recommendation lists, making diverse tradeoffs between multiple metrics and meeting the requirements of accuracy, novelty, diversity, and other user preferences. However, these algorithms are criticized for the low efficiency of the optimization process, especially when the number of users is large. To address this issue, this article proposes an evolutionary multitasking-based recommendation method, where each task corresponds to a user and all the tasks are optimized simultaneously, thus highly improving the efficiency of recommendation. To enhance the convergence speed, all the users are divided into multiple populations according to the similarity between their preferences, where each population evolves with internal knowledge transfer between users, and all the populations evolve with external knowledge transfer between populations. Experimental results on various datasets verify that the proposed method can better balance between multiple metrics than classical and deep neural network-based recommendation methods and exhibits significantly higher efficiency than evolutionary multiobjective optimization-based recommendation methods. © 2024 IEEE. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Edge-Cloud Cooperation-Driven intelligent Sustainability Evaluation Strategy Based on IoT and CPS for Energy-Intensive Manufacturing Industries

引用

IEEE Internet of Things Journal 2025年第9期12卷 12287-12297页

作者： Ma, Shuaiyin Huang, Yuming Chen, Yanping Xiao, Qinge Xu, Jun Leng, Jiewu Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an Key Laboratory of Big Data and Intelligent Computing School of Computer Science and Technology Xi’an710121 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Xidian University Advanced Manufacturing Technology Innovation Center Guangzhou Institute of Technology Guangzhou510555 China Guangdong University of Technology Guangdong Provincial Key Laboratory of Computer Integrated Manufacturing System State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment Guangzhou510006 China

The advancement of the Industry 5.0 in information technology has led to increased interest in integrating edge-cloud cooperation with Internet of Things (IoT) and cyber-physical system (CPS) designs. This integration effectively reduces service delays and provides real-time analysis feedback to physical spaces, attracting attention from both academia and industry. These advanced technologies enhance production system intelligence, their alignment with circular economy principles for promoting sustainability has been overlooked. To address this gap, this article proposes an intelligent sustainability evaluation strategy driven by edge-cloud cooperation, IoT, and CPS. The proposed approach aims to enhance production sustainability and intelligence through circular economy perspectives. It introduces improved gray relation analysis and deep clustering network techniques to extract meaningful insights from diverse indicators within the evaluation system. By analyzing relationships between different equipment and workshops, it provides an analytical method that enhances production efficiency while reducing energy consumption and resource waste. To further validate the proposed method, an illustrative example using a partner company’s production data demonstrates its accuracy. © 2014 IEEE.

关键词： Circular economy

来源：评论

学校读者我要写书评

暂无评论

Surface-Continuous Scene Representation for Light Field Depth Estimation via Planarity Prior

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第5期35卷 5051-5066页

作者： Chen, Rongshan Sheng, Hao Yang, Da Cui, Zhenglong Cong, Ruixuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing Hangzhou International Innovation Institute Zhejiang Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences China

Light field (LF) imaging captures both spatial and angular information of the real world, enabling precise depth estimation. However, images are merely discrete expressions of scenes. Limited by imaging technology, LF camera cannot capture the infinite rays emitted by scenes, leading to the discrete information storage (e.g. pixel). Consequently, previous deep learning methods have encountered challenges in accurately extracting depth information from LF images. In this paper, we investigate a surface-continuous scene representation using planarity prior and design PlaneNet, a Plane-based Network that successfully generates highly detailed depth maps for real scenes. Specifically, inspired by the plane assumption that real-world scenes generally yield piecewise smooth surfaces, we refine it to the pixel level for continuous surface approximation, which can overcome the limitations of discrete representation. Rather than explicitly parameterizing planes as multiple coefficients, we propose a novel plane regular sampling operator (PRSO), enabling the network to fit smooth depth surfaces easily. To explore the role of our theory at the feature level, we also introduce PRSO into the intermediate layers of PlaneNet. Experiments show that our method achieves state-of-the-art performance on both synthetic and real-world LF scenes, ranking 1st (MSE) on the HCI 4D Light Field benchmark. Furthermore, we explore the utilization of our representation in multiple LF depth estimation networks, and experiments demonstrate improved performance when surface-continuous representation is applied. © 1991-2012 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

arXiv

引用

arXiv 2025年

作者： Xi, Zekun Yin, Wenbiao Fang, Jizhan Wu, Jialong Fang, Runnan Zhang, Ningyu Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Tongyi Lab Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model’s predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, novelty, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, unoriginal, and repetitive outputs. To address these issues, we propose OmniThink, a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they slowly deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles. 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

IMPRESS: an importance-informed multi-tier prefix KV storage system for large language model inference 25

IMPRESS: an importance-informed multi-tier prefix KV storage...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Ruidong Zhang Siling Yang Ping Chen Yi Zheng Baoxing Huai Gang Chen The State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing The State Key Laboratory of Blockchain and Data Security Zhejiang University Huawei Cloud

ISBN: (纸本)9781939133458

Modern advanced large language model (LLM) applications often prepend long contexts before user queries to improve model output quality. These contexts frequently repeat, either partially or fully, across multiple queries. Existing systems typically store and reuse the keys and values of these contexts (referred to as prefix KVs) to reduce redundant computation and time to first token (TTFT). When prefix KVs need to be stored on disks due to insufficient CPU memory, reusing them does not always reduce TTFT, as disk I/O latency is high. In this paper, we propose IMPRESS, an importance-informed multi-tier prefix KV storage system to reduce I/O delay for LLM inference by only loading important prefix KVs. IMPRESS first leverages the insight that there is significant similarity in important token index sets across attention heads and introduces an I/O-efficient important KV identification algorithm. It then optimizes prefix KV storage and caching through importance-informed KV management, reducing TTFT during model inference. Our experimental results show that IMPRESS can reduce TTFT by up to 2.8× compared to state-of-the-art systems, while maintaining comparable inference accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical study of microorganisms swimming near a convex wall in a Giesekus fluid

引用

Physical Review E 2025年第1期111卷 015103-015103页

作者： Chenlin Zhu Fangyuan Peng Dingyi Pan Zhaosheng Yu Zhaowu Lin Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou 310018 China

The motion of microorganisms in complex fluids stands out as a prominent subject within fluid mechanics. In our study, we utilize the fictitious domain method to investigate the locomotion of squirmers along a convex wall in Giesekus viscoelastic fluids. This study examines the influence of fluid elasticity and wall curvature on squirmer particles, analyzing their movement patterns in detail. Near the convex wall, three distinct behavioral characteristics emerge: scattering, orbiting forward, and orbiting backward. The findings reveal that, compared with Newtonian fluids, squirmers exhibit a stronger tendency to be attracted toward the wall in viscoelastic fluids. This behavior is attributed to the elastic stress of the fluid, which generates a reverse torque on microbial particles, altering their movement direction and hindering their escape from the wall. Notably, as the wall curvature decreases, the likelihood of particles escaping diminishes.

关键词： Forward scattering

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: accelerating distributed GNN training leveraging feature-centric model migration 25

LeapGNN: accelerating distributed GNN training leveraging fe...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Xuechen Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University and Zhejiang Lab and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3.

关键词：

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：