检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ge, Jifeng Zhang, Juan Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan KeyLaboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This study presents a novel mixed-precision iterative refinement algorithm, GADI-IR, within the general alternating-direction implicit (GADI) framework, designed for efficiently solving large-scale sparse linear systems. By employing low-precision arithmetic, particularly half-precision (FP16), for computationally intensive inner iterations, the method achieves substantial acceleration while maintaining high numerical accuracy. key challenges such as overflow in half-precision and convergence issues for low precision are addressed through careful backward error analysis and the application of a regularization parameter α. Furthermore, the integration of low-precision arithmetic into the parameter prediction process, using Gaussian Process Regression (GPR), significantly reduces computational time without degrading performance. The method is particularly effective for large-scale linear systems arising from discretized partial differential equations and other high-dimensional problems, where both accuracy and efficiency are critical. Numerical experiments demonstrate that the use of mixed-precision strategies not only accelerates computation but also ensures robust convergence, making the approach advantageous for various applications. The results highlight the potential of leveraging lower-precision arithmetic to achieve superior computational efficiency in high-performance computing. © 2025, CC BY.

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Automatic Text Summarization Model for Judgment Documents 8th

A Hybrid Automatic Text Summarization Model for Judgment Doc...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Ouyang, Jianquan Huang, Wenpeng Liu, Tianming Key Laboratory of Intelligent Computing Information Processing Ministry of Education School of Computer Science and School of Cyberspace Science Xiangtan University Xiangtan China Department of Computer Science The University of Georgia AthensGA United States

ISBN: (纸本)9783031067662

Judgment documents are the final carrier of judicial trial activities, and they are an indispensable component for assisting sentencing decision-making and standardizing the scale of judgment. At present, the number of public judgment documents in China has reached 120 million, and it does not stop there, which brings a significant challenge for users to obtain useful information. To solve this problem, this paper proposes a hybrid automatic text summarization model for judgment documents. The method is divided into two stages. The first stage is, through extracting abstract technology, to extract key sentences from the original text to form a set of them. In the second stage, the set of key sentences extracted in the previous stage will be copied or rewritten to generate the final summary using the sequence generation model. The ROUGE indexes of this method in the automatic summarization experiment of judgment documents are 59.79, 37.71, and 52.67, which are 5.26, 7.25, and 10.41 higher than the benchmark model UniLM, respectively. The method proposed in this paper can effectively be applied in the automatic summarization service of judgment documents and solve the problem of information overload thereof and, finally, provide a new way for users to gain smooth access to judgment documents and information. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 2074-2083页

作者： Shoutao Guo Shaolei Zhang Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) Beijing China University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of AI Safety Chinese Academy of Sciences Beijing China

Simultaneous Machine Translation (SiMT) generates target translations in real-time while reading the source sentence. It relies on a policy to determine the optimal timing for producing translations, aiming to achieve both low response latency and high translation quality. Existing SiMT methods typically utilize the traditional Transformer architecture, employing complicated dynamic programming algorithms to jointly optimize policy decisions and translation generation. While these methods excel at determining policies, their translation capabilities are suboptimal. In contrast, Large Language Models (LLMs), trained on extensive corpora, exhibit exceptional generation capabilities but struggle to learn translation policies through traditional Transformer-based training methods. To address these limitations, we introduce Agent-SiMT, a novel framework combining the strengths of LLMs and traditional SiMT methods. Agent-SiMT contains a policy-decision agent and a translation agent. The policy-decision agent is managed by a SiMT model, which determines the policy using partial source sentences and translations. The translation agent, powered by an LLM, generates the target translation according to the policy decisions. These two agents work collaboratively to perform SiMT. Experiments demonstrate that our method attains state-of-the-art performance.

关键词： Translation Hidden Markov models Transformers Training Large language models Collaboration Vocabulary Speech processing Memory modules Machine translation

来源：评论

学校读者我要写书评

暂无评论

The grad-div conforming virtual element method for the quad-div problem in three dimensions

arXiv

引用

arXiv 2024年

作者： Dong, Xiaojing Han, Yibing Huang, Yunqing Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Er huan Road Hunan Xiangtan411105 China

We propose a new stable variational formulation for the quad-div problem in three dimensions and prove its well-posedness. Using this weak form, we develop and analyze the H(grad-div)-conforming virtual element method of arbitrary approximation orders on polyhedral meshes. Three families of H(grad-div)conforming virtual elements are constructed based on the structure of a de Rham sub-complex with enhanced smoothness, resulting in an exact discrete virtual element complex. In the lowest-order case, the simplest element has only one degree of freedom at each vertex and face, respectively. We rigorously prove the interpolation error estimates, the stability of discrete bilinear forms, the well-posedness of discrete formulation and the optimal error estimates. Some numerical examples are shown to verify the theoretical results. © 2024, CC BY-NC-ND.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization

Text-Driven Generative Domain Adaptation with Spectral Consi...

引用

International Conference on Computer Vision (ICCV)

作者： Zhenhuan Liu Liang Li Jiayu Xiao Zheng-Jun Zha Qingming Huang Institute of Computing Technology Key Laboratory of Intelligent Information Processing CAS University of Chinese Academy of Sciences University of Science and Technology of China Peng Cheng Laboratory

Combined with the generative prior of pre-trained models and the flexibility of text, text-driven generative domain adaptation can generate images from a wide range of target domains. However, current methods still suffer from overfitting and the mode collapse problem. In this paper, we analyze the mode collapse from the geometric point of view and reveal its relationship to the Hessian matrix of generator. To alleviate it, we propose the spectral consistency regularization to preserve the diversity of source domain without restricting the semantic adaptation to target domain. We also design granularity adaptive regularization to flexibly control the balance between diversity and stylization for target model. We conduct experiments for broad target domains compared with state-of-the-art methods and extensive ablation studies. The experiments demonstrate the effectiveness of our method to preserve the diversity of source domain and generate high fidelity target images. Source code has been released in https://***/Victarry/Adaptation-SCR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Policies of Subgoals for Safe Deep Reinforcement Learning 2nd

Hierarchical Policies of Subgoals for Safe Deep Reinforcem...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Yu, Fumin Gao, Feng Yuan, Yao Xing, Xiaofei Dai, Yinglong College of Information Science and Engineering Hunan Normal University Changsha410081 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China

ISBN: (纸本)9789819902712

Reinforcement learning is a machine learning method that relies on the agent to learn by trial and error to solve decision optimization problems. It is well known that an agent based on deep reinforcement learning in complex environments is difficult to train. Moreover, the agent will generate unsafe and strange actions due to the lack of sufficient reward feedback from the environment. To make the agent converge to a better policy and make its behavior safer and more controllable under sparse rewards, we propose a subgoal embedding method based on prior knowledge and hierarchical strategy that can make the training process converge faster. The subgoal embedding method can be combined with existing reinforcement learning methods. In this paper, we combine the subgoal embedding method with REINFORCE algorithm and PPO(Proximal Policy Optimization) algorithm to test the method in the MiniGrid-Doorkey game environment of the gym platform. The experiments demonstrate the effectiveness of the subgoal embedding method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. 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

No-Reference Image Quality Assessment Based on Active Reasoning Module 6

No-Reference Image Quality Assessment Based on Active Reason...

引用

6th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2023

作者： Qi, Junwei Deng, Yuhao Wang, Qingchun Yang, Zhen Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Shanghai Yanding Information Technology Co. Ltd. Shanghai201210 China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350399059

We present a no-reference image-quality - assessment algorithm based on active reasoning module. This algorithm has three modules: the feature extraction module, the active reasoning module, and the quality assessment module. The active reasoning module incorporates the generator component of the generative adversarial network and enhances its structure with the Res2Net architecture. By integrating this module into the backbone feature extraction network, we improve the receptive field of each convolutional layer, enabling the network to capture information at different scales of the image. To preserve the texture information of the image, we input the gradient map of the distorted image, the distorted image itself, and the image features generated by the generator into the quality assessment module, which has a multi-feature regression networks. This module establishes a mapping model from image-feature to image-quality scores. We conducted experimental analysis of this algorithm on three widely used public datasets, confirming the excellent performance and superiorities of the presented algorithm. The results validate the effectiveness of the designed algorithm and its ability to assess image quality accurately. © 2023 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning

arXiv

引用

arXiv 2023年

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes School of Electronic and Information Engineering Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation, and then uses two cross-attention modules to interact it with the features of the dual modalities respectively. In this way, the modality-specific information can well be activated in the multimodal representation. Finally, a feed-forward network is used to fuse two interacted multimodal representations for the further enhancement of the final multimodal representation. In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy. However, they either ignore the learning of single-modality branches or result in one branch failing to be well optimized. To solve these problems, we propose a dynamically guided learning algorithm that adaptively uses well-performing branches to guide the learning of other branches, for enhancing the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer sets a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets. In particular, the improvements of ProFormer on the LasHeR dataset are up to +6.2%/+ 4.1% in PR/SR compared with existing best RGBT tracker. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Model-Driven Federated Learning for Rational and Data-Efficient in Social Mobile Network

引用

IEEE Network 2024年

作者： Lu, Jianfeng Zhang, Ying Cao, Shuqin Wang, Wei Tang, Changbing Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China Zhejiang Normal University College of Physics and Electronic Information Engineering Jinhua321004 China

With the rise of data-intensive services in mobile networks, the demand for intelligent and efficient learning frameworks has grown exponentially. Federated Learning (FL), as an emerging paradigm, enables decentralized edge devices to collaboratively train large models without sharing raw data, ensuring privacy preservation. However, deploying FL in resource-constrained mobile environments faces significant challenges, such as free-riding and malicious behavior. These challenges hinder model performance and raise concerns about data integrity and inter-user cooperation. To address these issues, we propose a layered dynamic framework for social mobile networks, called FedSMN, which aims to enhance the generalization ability of collaboratively trained large models in FL environments. FedSMN leverages Bayesian inference to evaluate user behavior and employs evolutionary game theory to simulate dynamic interactions, thereby optimizing cooperation strategies and reducing communication overhead. Unlike traditional approaches that assume fully rational actors, FedSMN accounts for irrational behavior and fluctuating resources, designing an efficient incentive mechanism to improve data utilization. Extensive experiments on large-scale datasets demonstrate that FedSMN increases model accuracy by 21% and reduces communication overhead by 49%, paving the way for scalable, intelligent mobile networks powered by large models. © 1986-2012 IEEE.

关键词： Collaborative learning

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：