检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Yonghao Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University China University of Trento Italy

ISBN: (纸本)157735897X

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Instance-adaptive Zero-shot Chain-of-Thought Prompting 38

Instance-adaptive Zero-shot Chain-of-Thought Prompting

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yuan, Xiaosong Shen, Chen Yan, Shaotian Zhang, Xiaofeng Xie, Liang Wang, Wenxiao Guan, Renchu Wang, Ying Ye, Jieping College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MoE Jilin University China Alibaba Cloud Computing China Shanghai Jiao Tong University China College of Computer Science and Technology Zhejiang University of Technology China College of Software Zhejiang University China

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8k, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global methyl halide emissions from biomass burning during 2003-2021

引用

Environmental science and Ecotechnology 2023年第2期14卷 79-86页

作者： Xiaoyi Hu Di Chen Liting Hu Bowei Li Xinhe Li Xuekun Fang College of Environmental&Resource Sciences Zhejiang UniversityHangzhouZhejiang310058PR China State Key Joint Laboratory for Environmental Simulation and Pollution Control College of Environmental Sciences and EngineeringPeking UniversityBeijing100871PR China Center for Global Change Science Massachusetts Institute of TechnologyCambridgeMA02139USA

Methyl halides(CH3Cl,CH3Br,and CH3I)are ozone-depleting *** burning(BB)is an important source of methyl *** temporal variations and global spatial distribution of BB methyl halide emissions are ***,global methyl halide emissions from BB during 2003e2021 were estimated based on satellite data.A significant decreasing trend(p<0.01)in global methyl halide emissions from BB was found between 2003 and 2021,with CH3Cl emissions decreasing from 302 to 220 Gg yr^(-1),CH3Br emissions decreasing from 16.5 to 11.7 Gg yr^(-1),and CH3I emissions decreasing from 8.9 to 6.1 Gg yr^(-1).From a latitudinal perspective,the northern high-latitude region(60e90N)was the only latitude zone with significant increases in BB methyl halide emissions(p<0.01).Based on an analysis of the drivers of BB methyl halide emissions,emissions from cropland,grassland,and shrubland fires were more correlated with the burned area,while BB emissions from forest fires were more correlated with the emissions per unit burned *** non-BB emissions of CH3Cl increased from 4749 Gg yr^(-1)in 2003 to 4882 Gg yr^(-1)in 2020,while those of CH3Br decreased from 136 Gg yr^(-1)in 2003 to 118 Gg yr^(-1)in 2020(global total CH3I emissions are not available).The finding indicates that global CH3Cl and CH3Br emissions from sources besides BB increased and decreased during *** on our findings,not only searching for unknown sources is important,but also re-evaluating known sources is necessary for addressing methyl halide emissions.

关键词： Methyl halides Biomass burning Emission inventory Global budget Ozone depletion

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sliding Mode Control for Automotive Electronic Throttle based on Extremum Seeking

Adaptive Sliding Mode Control for Automotive Electronic Thro...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Lin Chen Jinwu Gao Jilin University and the Department of Control Science and Engineering State Key Laboratory of Automotive Simulation and Control Jilin University Changchun China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

With the help of extremum seeking (ES), an improved adaptive sliding mode control (ES-ASMC) method is proposed to accomplish rapid and precise servo control of throttle angle. Some existing adaptive sliding mode control schemes applied to electronic throttle focus only on the switching gain, with limited attention to other parameters. While in the method presented in this study, all parameters of the sliding mode control (SMC) law are optimized simultaneously. An objective function is designed to measure the tracking error, which is subsequently reduced by ES with gradient descent to obtain a more favorable tracking response. In addition, a tracking differentiator is introduced to suppress the measurement noise of the output signal in place of the regular differentiator. Eventually, hardware experiments are conducted in an electronic throttle control (ETC) system to validate the effectiveness of the proposed approach. Comparison with other solutions reveals the superiority of the ES-ASMC in terms of tracking accuracy and response speed.

关键词： Accuracy Noise Switches Linear programming Hardware Trajectory Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Research progress and development trend of coastal wetland restoration in greater bay areas

引用

Watershed Ecology and the Environment 2022年 4卷 177-187页

作者： Yu, Shuling Cui, Baoshan Xie, Tian Wang, Qing Yan, Jiaguo Ning, Zhonghua State Key Laboratory of Water Environment Simulation School of Environment Beijing Normal University Beijing 100875 China School of Environmental Science and Engineering Tiangong University Tianjin 300387 China

We explored the potential for functional processes maintenance principles to be applied in coastal restoration. Greater bay areas are located in the transition zone between land and sea. Coastal wetlands play a key role in the ecological environment construction of greater bay areas. Due to the dual effects of high-intensity human activities and climate change, coastal wetlands in greater bay areas have suffered varying degrees of damage, including reduced area, habitat degradation, and impaired ecological functions. However, the research progress and development trend of restoration of damaged coastal wetland ecosystems has not yet been revealed, and the application theory of functional processes in coastal restoration is still unclear. Based on extensive literature research, our study reviewed the mechanisms and types of coastal wetland ecosystem restoration in greater bay areas. Coastal wetland ecosystem restoration technologies and methods are mainly based on the biological, hydrological, and chemical processes in greater bay areas. The current research progress and existing deficiencies of coastal wetland ecosystem restoration in greater bay areas are clarified. Combining years of research background in the coastal wetland field, focusing on the importance and criticality of coastal wetland functional processes to maintaining ecosystem functions, the main future research trends are proposed, which will solve the principal theory facing the restoration of coastal wetland ecosystems in greater bay areas. Our study will promote the application of new concepts and new techniques of coastal wetland restoration nationwide, and improve the overall level of ecological restoration in coastal wetland. © 2022 The Authors

关键词： Biological process Chemical process Coastal wetland Ecological restoration Greater bay areas Hydrological process

来源：评论

学校读者我要写书评

暂无评论

Design of Ultra-Stable Solid Amine Adsorbents and Mechanisms of Hydroxyl Group-Dependent Deactivation for Reversible CO2 Capture from Flue Gas

引用

Nano-Micro Letters 2025年第7期 363-381页

作者： Meng Zhao Liang Huang Yanshan Gao Ziling Wang Shuyu Liang Xuancan Zhu Qiang Wang Hong He Dermot O'Hare College of Environmental Science and Engineering Beijing Forestry University State Key Laboratory of Efficient Production of Forest Resources Beijing Forestry University Research Center of Solar Power and Refrigeration Institute of Refrigeration and CryogenicsShanghai Jiao Tong University State Key Joint Laboratory of Environment Simulation and Pollution Control Research Centre for Eco-Environmental SciencesChinese Academy of Sciences Chemistry Research Laboratory Department of ChemistryUniversity of Oxford

Although supported solid amine adsorbents have attracted great attention for CO2capture,critical chemical deactivation problems including oxidative degradation and urea formation have severely restricted their practical applications for flue gas *** this work,we reveal that the nature of surface hydroxyl groups （metal hydroxyl Al–OH and nonmetal hydroxyl Si–OH） plays a key role in the deactivation *** polyethyleneimine （PEI） supported on Al–OH-containing substrates suffers from severe oxidative degradation during the CO2capture step due to the breakage of amine-support hydrogen bonding networks,but exhibits an excellent anti-urea formation feature by preventing dehydration of carbamate products under a pure CO2regeneration *** contrast,PEI supported on Si–OH-containing substrates exhibits excellent anti-oxidative stability under simulated flue gas conditions by forming a robust hydrogen bonding protective network with Si–OH,but suffers from obvi- ous urea formation during the pure CO2regeneration *** also reveal that the urea formation problem for PEI-SBA-15 can be avoided by the incorporation of an OH-containing PEG *** on the intrinsic understanding of degradation mechanisms,we successfully synthesized an adsorbent 40PEI-20PEG-SBA-15 that demonstrates outstanding stability and retention of a high CO2capacity of 2.45 mmol g-1over 1000 adsorption–desorption cycles,together with negligible capacity loss during aging in simulated flue gas （10%CO2+5%O2+3%H2O） for one month at60–70℃.We believe this work makes great contribution to the advancement in the field of ultra-stable solid amine-based CO2capture materials.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Creativity Enhancement Method Based on Emotional Analysis and Concentration

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 1019-1048页

作者： Liu, Chang Zhang, Longfei Huang, Tianyu Wu, Yufeng Zhang, Fuquan Lin, Qi Department of Computer Science and Technology Beijing Institute of Technology 100081 China Beijing Key Laboratory of Digital Performance and Simulation Technology 100081 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Informatics King’s College London LondonWC2R 2LS United Kingdom

Intelligent performance creativity is a new research direction of the intersection of technology and art. At present, the cutting-edge technologies such as computer simulation, emotional computing and machine learning have been applied to the evaluation and enhancement of intelligent performance creativity. The application of these technologies has greatly increased the diversity of performance forms and the complexity of performance content. For the traditional stage performance, due to the lack of timely feedback from the audience, it is difficult for the director to enhance the creativity effec-tively. In order to solve this problem, this paper proposes concentration level enhancement method (CLEM). The CLEM extracts and analyzes the physiological and emotional characteristics of the audience by collecting the multimodal physiological signal data of the audience. Through the analysis of the features, the concentration information of the audience is obtained and the concentration level (CL) is defined. Based on the physiological and emotional induction mechanism, a performance creativity enhancement strategy is proposed, which enhances the performance creativity in two aspects: " Visual-based" and " Content-based". Through the concentration level enhancement method, compare the audience’s performance attention changes before and after the performance creativity enhancement, select the effective strategies to enhance the performance creativity, and provide the director with quantifiable performance creativity enhancement feedback results. The experimental results show that the CLEM proposed in this paper can effectively induce significant changes in the audience’s emotion, and the selected creative enhancement strategy can significantly improve the audience’s concentration and achieve the purpose of enhancing the creativity of the performance. © 2023, Journal of Network Intelligence.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

3D Face Alignment and Face Reconstruction Based on Image Sequence 14

3D Face Alignment and Face Reconstruction Based on Image Seq...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Wei, Yao Qiao, Biao Wang, Huabin Zhang, Mengxin Liu, Shijun Tao, Liang Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China School of Computer Science and Information Engineering Bengbu University Bengbu China

ISBN: (纸本)9781510657564

Existing 3D face alignment and face reconstruction methods mainly focus on the accuracy of the model. When the existing methods are applied to dynamic videos, the stability and accuracy are significantly reduced. To overcome this problem, we propose a novel regression framework that strikes a balance between accuracy and stability. First, on the basis of lightweight backbone, encoder-decoder structure is used to jointly learn expression details and detailed 3D face from video images to recover shape details and their relationship to facial expression, and dynamic regression of a small number of 3D face parameters, effectively improve the speed and accuracy. Secondly, in order to further improve the stability of face landmarks in video, a jitter loss function of multi-frame image joint learning is proposed to strengthen the correlation between frames and face landmarks in video, and reduce the difference amplitude of face landmarks between adjacent frames to reduce the jitter of face landmarks. Experiments on several challenging datasets verify the effectiveness of our method. © 2022 SPIE.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

A Unified Loss for Handling Inter-Class and Intra-Class Imbalance in Medical Image Segmentation 39

A Unified Loss for Handling Inter-Class and Intra-Class Imba...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Feilong Yang, Feiyang Li, Xiongfei Zhang, Xiaoli Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Jilin University China

ISBN: (纸本)157735897X

In utilizing deep learning techniques for medical image segmentation, two types of imbalance issues are observed: inter-class imbalance between majority and minority classes and intra-class imbalance between easy and hard samples. However, existing loss functions typically confuse these issues, leading to enhancements that cater to only one aspect. Moreover, loss functions optimized for specific tasks often exhibit limited generalizability. To address these issues, we propose Inter-class and Intra-class Balance loss, as well as a unified loss termed Balance loss. The Inter-class Balance loss controls the extent of hard sample mining for majority class samples by considering the frequency of minority classes present in each input image. This approach requires no manual adjustment weights and adapts automatically to different datasets. The Intra-class Balance loss enhances the network's ability to learn from hard samples by performing mining on hard samples within each class. We evaluate our loss functions on five segmentation tasks with varying degrees of class imbalance. The experimental results show that our proposed Balance loss enhances segmentation performance compared with the current loss functions and exhibits superior robustness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast θ -Maruyama scheme for stochastic Volterra integral equations of convolution type: mean-square stability and strong convergence analysis

引用

computational and Applied Mathematics 2023年第3期42卷

作者： Wang, Mengjie Dai, Xinjie Yu, Yanyan Xiao, Aiguo Hunan Key Laboratory for Computation and Simulation in Science and Engineering National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China School of Mathematics and Statistics Yunnan University Yunnan Kunming650504 China

In this paper, a fast θ-Maruyama method is proposed for solving stochastic Volterra integral equations of convolution type with singular and Hölder continuous kernels based on the sum-of-exponentials approximation. Furthermore, the average storage O(N) and the calculation cost O(N2) of θ-Maruyama scheme are reduced to O(log N) and O(Nlog N) for T 1 or O(log 2N) and O(Nlog 2N) for T≈ 1 , respectively, which implies that the fast θ-Maruyama scheme is confirmed to improve the computational efficiency of the θ-Maruyama method. Under the local Lipschitz and linear growth conditions, strong convergence of the given numerical scheme are obtained. Then, for the linear test equation, we show the asymptotic behavior of solutions in mean square sense. Further, we obtain the explicit structure of the stability matrices and some numerical results of the mean-square stability for the fast θ-Maruyama method applied to the linear test equation. Finally, some numerical experiments are also given to illustrate the effectiveness of the method. © 2023, The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional.

关键词： computational efficiency

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：