检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Liuwen He, Hongkui Huang, Hailin Wang, Jiexin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9798891761964

Automatic code summarization aims to generate concise natural language descriptions (summary) for source code, which can free software developers from the heavy burden of manual commenting and software maintenance. Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the significant heterogeneity gap between code and summary. Moreover, existing methods lack a human-like re-check process to evaluate whether the generated summaries match well with the code. To address these two limitations, we introduce RBCoSum, a novel framework that incorporates the generated Chain Of Comments (COC) as auxiliary intermediate information for the model to bridge the gap between code and summaries. Also, we propose a rethinking process where a learned ranker trained on our constructed ranking dataset scores the extent of matching between the generated summary and the code, selecting the highest-scoring summary to achieve a re-check process. We conduct extensive experiments to evaluate our approach and compare it with other automatic code summarization models as well as multiple code Large Language Models (LLMs). The experimental results show that RBCoSum is effective and outperforms baselines by a large margin. The human evaluation also proves the summaries generated with RBCoSum are more natural, informative, useful, and truthful. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Joint Estimation of SOH and RUL for Lithium-Ion Batteries Based on Improved Twin Support Vector Machineh

引用

Energy Engineering 2025年第1期122卷 243-264页

作者： Liyao Yang Hongyan Ma Yingda Zhang Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Institute of Distributed Energy Storage Safety Big Data Beijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044China

Accurately estimating the State of Health(SOH)and Remaining Useful Life(RUL)of lithium-ion batteries(LIBs)is crucial for the continuous and stable operation of battery management ***,due to the complex internal chemical systems of LIBs and the nonlinear degradation of their performance,direct measurement of SOH and RUL is *** address these issues,the Twin Support Vector Machine(TWSVM)method is proposed to predict SOH and ***,the constant current charging time of the lithium battery is extracted as a health indicator(HI),decomposed using Variational Modal Decomposition(VMD),and feature correlations are computed using Importance of Random Forest Features(RF)to maximize the extraction of critical factors influencing battery performance ***,to enhance the global search capability of the Convolution Optimization Algorithm(COA),improvements are made using Good Point Set theory and the Differential Evolution *** Improved Convolution Optimization Algorithm(ICOA)is employed to optimize TWSVM parameters for constructing SOH and RUL prediction ***,the proposed models are validated using NASA and CALCE lithium-ion battery *** results demonstrate that the proposed models achieve an RMSE not exceeding 0.007 and an MAPE not exceeding 0.0082 for SOH and RUL prediction,with a relative error in RUL prediction within the range of[-1.8%,2%].Compared to other models,the proposed model not only exhibits superior fitting capability but also demonstrates robust performance.

关键词： State of health remaining useful life variational modal decomposition random forest twin support vector machine convolutional optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching for transformer-based weakly supervised object localization

引用

PATTERN RECOGNITION 2025年 158卷

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao South China Univ Technol Sch Software Engn Guangzhou Peoples R China Peng Cheng Lab Shenzhen Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China

Weakly supervised object localization (WSOL) strives to localize objects with only image-level supervision. WSOL often faces challenges such as incomplete localization due to classifier bias and over-localization in real scenes where objects and backgrounds are strongly associated or structurally similar. While the latest Transformer-based methods effectively enhance localization performance by leveraging long-range feature dependencies, they may inadvertently amplify divergent background activation and remain susceptible to classification bias. To this end, we proposed a novel Se mantic-Constraint C onstraint M atching (SeCM) plug-in module tailored for transformer-based approaches. In detail, a local patch shuffle strategy is first introduced to disentangle partial contextual linkages, thereby creating image pairs. Then a semantic matching module extracts co-object knowledge from the primal-shuffled image pairs, drives the network to identify the association of foreground with semantic label to suppress divergent activation. Moreover, to alleviate incomplete localization and prevent excessive suppression of activation, we propose leveraging multi-modal class-specific textual representations to guide object localization by complementing intra-class priori diverse knowledge. Extensive experimental results conducted on CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance.

关键词： Weakly-supervised object localization Vision transformer Image matching Vision language model

来源：评论

学校读者我要写书评

暂无评论

A Frequency and Polarization Reconfigurable Transparent Water Antenna

引用

Progress in Electromagnetics Research C 2025年 152卷 177-186页

作者： Li, Lei Gao, Jing Nan, Jingchang School of Electronics and Information Engineering Liaoning Technical University Huludao125105 China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Huludao125105 China

A novel frequency and polarization reconfigurable water patch antenna is proposed for radio communication in the UHF band. Based on theoretical analysis and simulation results, water is an ideal material for designing transparent liquid ground. Water enhances outstanding transparency, excellent aesthetics, and high optical stealth performance for a wider range of application scenarios. The entire structure is made with polyvinyl chloride material and distilled water, except for the feed structure. By filling different cavities with liquid water, five different operating states are obtained in 1.924–2.5 GHz (26.1%), 1.67–2.33 GHz (33%), 0.644–2.288 GHz (112.1%), 1.975–2.54 GHz (25%), and 1.748–2.108 GHz (18.7%), achieving frequency reconfigurability. The antenna can be flexibly switched between linear polarization (LP) and two right-handed circular polarization (RHCP) states. The results show that the 3 dB axial ratio (AR) bandwidth covers 1.93–2.08 GHz (7.5%) and 2.06–2.132 GHz (3.5%). The antenna achieves high optical transparency of 100% and a peak gain of 7.97 dBi. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Circular polarization

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 23

IMPRESS: An Importance-Informed Multi-Tier Prefix KV Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Chen, Weijian He, Shuibing Qu, Haoyang Zhang, Ruidong Yang, Siling Chen, Ping Zheng, Yi Huai, Baoxing Chen, Gang The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Huawei Cloud China

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. © 2025 FAST. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Device-edge collaborative occluded face recognition method based on cross-domain feature fusion

引用

Digital Communications and Networks 2025年第2期11卷 482-492页

作者： Puning Zhang Lei Tan Zhigang Yang Fengyi Huang Lijun Sun Haiying Peng School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Chongqing Innovation Center of Industrial Big-Data Co.Lt

The lack of facial features caused by wearing masks degrades the performance of facial recognition systems. Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer and the device layer. Besides, previous research fails to consider the facial characteristics including occluded and unoccluded parts. To solve the above problems, we put forward a device-edge collaborative occluded face recognition method based on cross-domain feature fusion. Specifically, the device-edge collaborative face recognition architecture gets the utmost out of maximizes device and edge resources for real-time occluded face recognition. Then, a cross-domain facial feature fusion method is presented which combines both the explicit domain and the implicit domain facial. Furthermore, a delay-optimized edge recognition task scheduling method is developed that comprehensively considers the task load, computational power, bandwidth, and delay tolerance constraints of the edge. This method can dynamically schedule face recognition tasks and minimize recognition delay while ensuring recognition accuracy. The experimental results show that the proposed method achieves an average gain of about 21% in recognition latency, while the accuracy of the face recognition task is basically the same compared to the baseline method.

关键词： Occluded face recognition Cross-domain feature fusion Device-edge collaboration

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV air combat cooperative game based on virtual opponent and value attention decomposition policy gradient

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 267卷

作者： Xu, Xiaojie Wang, Yunfan Guo, Xian Huang, Kuihua Zhang, Xuebo Nankai Univ Inst Robot & Automat Informat Syst Coll Artificial Intelligence Tianjin Peoples R China Nankai Univ Tianjin Key Lab Intelligent Robot Tianjin Peoples R China Natl Univ Def Technol Coll Syst Engn Lab Big Data & Decis Changsha 410073 Peoples R China

In the multi-unmanned aerial vehicle (UAV) air combat confrontation environment, deriving the cooperative policy of friendly aircraft is still a challenge, owing to the higher-order differential dynamics model of aircraft and the confidence assignment problem in multi-UAV air combat with conflict and cooperation. In this paper, a novel reinforcement learning method that combines virtual opponent and value attention decomposition is proposed. In particular, to reduce the difficulty in training induced by the higher order differential dynamics model, the actions of aircraft are abstracted into actions of the game layer and maneuvering actions of the bottom layer, in which the actions of the game layer are modeled as the pose of the virtual opponent. In the training process, only the policy of the game layer is trained, and the maneuvering policy of the bottom layer is the default policy or the rule-based policy. To address the confidence assignment problem encountered during multi-UAV cooperative training, the total value function of the team is decomposed into individual value functions based on the attention mechanism, and the policy of the game layer is optimized by integrating the individual value into the gradient computation as the baseline. Finally, the algorithm is verified on the dynamic high-fidelity training platform. The results indicate that the algorithm outperforms the state-of-the-art method in typical multi-UAV air combat scenarios such as 4V4, 5V5, and 6V6.

关键词： Air combat cooperative game Reinforcement learning Value attention decomposition

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Xi’an710049 China Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China Peking University School of Computer Science Beijing100871 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University Xi'an710049 China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports 3.12x more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

T-Assess: An Efficient data Quality Assessment System Tailored for Trajectory data 51st

T-Assess: An Efficient Data Quality Assessment System Tailor...

引用

51st International Conference on Very Large data Bases, VLDB 2025

作者： Zhu, Junhao Wang, Tao Hu, Danlei Fang, Ziquan Chen, Lu Gao, Yunjun Li, Tianyi Jensen, Christian S. Zhejiang University China Zhejiang University Zhejiang Key Laboratory of Big Data Intelligent Computing China Aalborg University Denmark

With the widespread use of GPS-enabled devices and services, trajectory data fuels services in a variety of fields, such as transportation and smart cities. However, trajectory data often contains errors stemming from inaccurate GPS measurements, low sampling rates, and transmission interruptions, yielding low-quality trajectory data with negative effects on downstream services. Therefore, a crucial yet tedious endeavor is to assess the quality of trajectory data, serving as a guide for subsequent data cleaning and analyses. Despite some studies addressing general-purpose data quality assessment, no studies exist that are tailored specifically for trajectory data. To more effectively diagnose the quality of trajectory data, we propose T-Assess, an automated trajectory data quality assessment system. T-Assess is built on three fundamental principles: i) extensive coverage, ii) versatility, and iii) efficiency. To achieve comprehensive coverage, we propose assessment criteria spanning validity, completeness, consistency, and fairness. To provide high versatility, T-Assess supports both offline and online evaluations for full-batch trajectory datasets as well as real-time trajectory streams. In addition, we incorporate an evaluation optimization strategy to achieve assessment efficiency. Extensive experiments on fourreal-life benchmark datasets offer insight into the effectiveness of T Assess at quantifying trajectory data quality beyond the capabilities of state-of-the-art data quality systems. © 2025, VLDB Endowment, All rights reserved.

关键词： data quality

来源：评论

学校读者我要写书评

暂无评论

Rational molecular design of P-doped porous carbon material for the VOCs adsorption

引用

Chinese Journal of Chemical Engineering 2025年第3期79卷 155-163页

作者： Changqing Su Wentao Jiang Yang Guo Guodong Yi Zengxing Li Huan Li Hunan Key Laboratory of Carbon Neutrality and Intelligent Energy School of Resources & Environment Hunan University of Technology and Business Xiangjiang Laboratory School of Advanced Interdisciplinary Studies Research Institute for Big Data & Internet Innovation Hunan University of Technology and Business Industry Training Center Shenzhen Polytechnic University

The objective of this study was to identify and synthesize functional groups for the efficient adsorption of volatile organic compounds（VOCs） through a combination of theoretical calculations,molecular design,and experimental *** density functional theory（DFT） calculation,focusing on the P-containing functional groups,showed that methanol adsorption was dominated by the electrostatic interaction between the carbon surface and methanol,while toluene was mainly trapped through π-π dispersive interaction between toluene molecule and functional group *** experimental results showed the phosphorus-doped carbon materials（PCAC） prepared by directly activating potassium phytate had a phosphorus content of up to 4.5%（atom）,mainly in the form of C—O—P（O）(OH)*** material exhibited a high specific area(987.6 m2·g-1) and a large adsorption capacity for methanol(440.0 mg·g-1) and toluene(350.1 mg·g-1).These properties were superior to those of the specific commercial activated carbon（CAC）sample used for comparison in this *** adsorption efficiencies per unit specific surface area of PCAC were 0.45 mg·g-1m2for methanol and 0.35 mg·g-1·m-2for *** study provided a novel theoretical and experimental framework for the molecular design of polarized elements to enhance the adsorption of polar gases,offering significant advancements over existing commercial solutions.

关键词： Adsorption Density functional theory Doped porous carbon Molecular design VOCs

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

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

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：