检索结果-内蒙古大学图书馆

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 841-858页

作者： Luolin Xiong Haofen Wang Xi Chen Lu Sheng Yun Xiong Jingping Liu Yanghua Xiao Huajun Chen Qing-Long Han Yang Tang Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education and the Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai China College of Design and Innovation Tongji University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Software Beihang University Beijing China School of Information Science and Engineering East China University of Science and Technology Shanghai China AZFT Joint Laboratory for Knowledge Engine Hangzhou Innovation Center College of Computer Science and Technology Zhejiang University Hangzhou China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia

DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek's engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek's innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning.

关键词： Training Technological innovation Foundation models Large language models Reinforcement learning Prediction algorithms Market research Cognition Inference algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

arXiv

引用

arXiv 2025年

作者： Jiao, Yingying Wang, Zhigang Wu, Sifan Fan, Shaojing Liu, Zhenguang Xu, Zhuoyue Wu, Zheqi College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal pose heatmaps and visual features. To address these limitations, we introduce STDPose, a novel framework that enhances human pose estimation by learning spatiotemporal dynamics in sparsely-labeled videos. STDPose incorporates two key innovations: 1) A novel Dynamic-Aware Mask to capture long-range motion context, allowing for a nuanced understanding of pose changes. 2) A system for encoding and aggregating spatiotemporal representations and motion dynamics to effectively model spatiotemporal relationships, improving the accuracy and robustness of pose estimation. STDPose establishes a new performance benchmark for both video pose propagation (i.e., propagating pose annotations from labeled frames to unlabeled frames) and pose estimation tasks, across three large-scale evaluation datasets. Additionally, utilizing pseudo-labels generated by pose propagation, STDPose achieves competitive performance with only 26.7% labeled data. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Generalization on Graphs via Progressive Inference

arXiv

引用

arXiv 2025年

作者： Xu, Yiming Shi, Bin Peng, Zhen Liu, Huixiang Dong, Bo Chen, Chen School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China University of Virginia CharlottesvilleVA United States

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%. 1 © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of UAV-Carried IRS for Urban Low Altitude mmWave Communications with Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Xie, Wenwen Sun, Geng Liu, Bei Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit Kim, Dong In The College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The University of Hong Kong 999077 Hong Kong The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Emerging technologies in sixth generation (6G) of wireless communications, such as terahertz communication and ultra-massive multiple-input multiple-output, present promising prospects. Despite the high data rate potential of millimeter wave communications, millimeter wave (mmWave) communications in urban low altitude economy (LAE) environments are constrained by challenges such as signal attenuation and multipath interference. Specially, in urban environments, mmWave communication experiences significant attenuation due to buildings, owing to its short wavelength, which necessitates developing innovative approaches to improve the robustness of such communications in LAE networking. In this paper, we explore the use of an unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) to support low altitude mmWave communication. Specifically, we consider a typical urban low altitude communication scenario where a UAV-carried IRS establishes a line-of-sight (LoS) channel between the mobile users and a source user (SU) despite the presence of obstacles. Subsequently, we formulate an optimization problem aimed at maximizing the transmission rates and minimizing the energy consumption of the UAV by jointly optimizing phase shifts of the IRS and UAV trajectory. Given the non-convex nature of the problem and its high dynamics, we propose a deep reinforcement learning-based approach incorporating neural episodic control, long short-term memory, and an IRS phase shift control method to enhance the stability and accelerate the convergence. Simulation results show that the proposed algorithm effectively resolves the problem and surpasses other benchmark algorithms in various performances. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

NSPG-Miner: Mining Repetitive Negative Sequential Patterns

arXiv

引用

arXiv 2025年

作者： Li, Yan Wang, Zhulin Liu, Jing Guo, Lei Fournier-Viger, Philippe Wu, Youxi Wu, Xindong School of Economics and Management Hebei University of Technology Tianjin300401 China School of Artificial Intelligence Hebei University of Technology Tianjin300401 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin300401 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China Hebei Key Laboratory of Big Data Computing 300401 China Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology Hefei230009 China

Sequential pattern mining (SPM) with gap constraints (or repetitive SPM or tandem repeat discovery in bioinformatics) can find frequent repetitive subsequences satisfying gap constraints, which are called positive sequential patterns with gap constraints (PSPGs). However, classical SPM with gap constraints cannot find the frequent missing items in the PSPGs. To tackle this issue, this paper explores negative sequential patterns with gap constraints (NSPGs). We propose an efficient NSPG-Miner algorithm that can mine both frequent PSPGs and NSPGs simultaneously. To effectively reduce candidate patterns, we propose a pattern join strategy with negative patterns which can generate both positive and negative candidate patterns at the same time. To calculate the support (frequency of occurrence) of a pattern in each sequence, we explore a NegPair algorithm that employs a key-value pair array structure to deal with the gap constraints and the negative items simultaneously and can avoid redundant rescanning of the original sequence, thus improving the efficiency of the algorithm. To report the performance of NSPG-Miner, 11 competitive algorithms and 11 datasets are employed. The experimental results not only validate the effectiveness of the strategies adopted by NSPG-Miner, but also verify that NSPG-Miner can discover more valuable information than the state-ofthe-art algorithms. Algorithms and datasets can be downloaded from https://***/wuc567/PatternMining/tree/master/NSPG-Miner. Copyright © 2025, The Authors. All rights reserved.

关键词： Miners

来源：评论

学校读者我要写书评

暂无评论

PEJA:Progressive Energy-Efficient Join Processing for Sensor Networks

引用

Journal of Computer Science & Technology 2008年第6期23卷 957-972页

作者：赖永炫陈毅隆陈红 School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education

Sensor networks are widely used in many applications to collaboratively collect information from the physical environment. In these applications, the exploration of the relationship and linkage of sensing data within multiple regions can be naturally expressed by joining tuples in these regions. However, the highly distributed and resource-constraint nature of the network makes join a challenging query. In this paper, we address the problem of processing join query among different regions progressively and energy-efficiently in sensor networks. The proposed algorithm PEJA （Progressive Energy-efficient Join Algorithm） adopts an event-driven strategy to output the joining results as soon as possible, and alleviates the storage shortage problem in the in-network nodes. It also installs filters in the joining regions to prune unmatchable tuples in the early processing phase, saving lots of unnecessary transmissions. Extensive experiments on both synthetic and real world data sets indicate that the PEJA scheme outperforms other join algorithms, and it is effective in reducing the number of transmissions and the delay of query results during the join processing.

关键词： progressive join minimal join set in-network processing sensor network

来源：评论

学校读者我要写书评

暂无评论

GKG-LLM: A Unified Framework for Generalized knowledge Graph Construction

arXiv

引用

arXiv 2025年

作者： Zhang, Jian Wei, Bifan Qi, Shihao Zhu, Haiping Liu, Jun Lin, Qika School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China National University of Singapore Singapore

The construction of Generalized knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. Copyright © 2025, The Authors. All rights reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Medical Image Segmentation Based on Frequency Domain Aware Stable Consistency Regularization

引用

Journal of imaging informatics in medicine 2025年 2025 Jan 22页

作者： Yihao Ouyang Peipei Li Haixiang Zhang Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei 230009 Anhui China. School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 Anhui China. School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 Anhui China. peipeili@***. Center for Big Data and Population Health of IHM Anhui Medical University Hefei Anhui China. peipeili@***. Center for Big Data and Population Health of IHM Anhui Medical University Hefei Anhui China. Computer Centre The Second People's Hospital of Hefei Hefei 230011 Anhui China. Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of Technology Hefei 230009 Anhui China.

With the advancement of deep learning models nowadays, they have successfully applied in the semi-supervised medical image segmentation where there are few annotated medical images and a large number of unlabeled ones. A representative approach in this regard is the semi-supervised method based on consistency regularization, which improves model training by imposing consistency constraints (perturbations) on unlabeled data. However, the perturbations in this kind of methods are often artificially designed, which may introduce biases unfavorable to the model learning in the handling of medical image segmentation. On the other hand, the majority of such methods often overlook the supervision in the Encoder stage of training and primarily focus on the outcomes in the later stages, potentially leading to chaotic learning in the initial phase and subsequently impacting the learning process of the model in the later stages. At the meanwhile, they miss the intrinsic spatial-frequency information of the images. Therefore, in this study, we propose a new semi-supervised medical image segmentation approach based on frequency domain aware stable consistency regularization. Specifically, to avoid the bias introduced by artificially setting perturbations, we first utilize the inherent frequency domain information of images, including both high and low frequencies, as the consistency constraint. Secondly, we incorporate supervision in the Encoder stage of model training to ensure that the model does not fail to learn due to the disruption of the original feature space caused by strong augmentation. Finally, extensive experimentation validates the effectiveness of our semi-supervised approach.

关键词： Consistency regularization Frequency domain Medical image segmentation Semi-supervision

来源：评论

学校读者我要写书评

暂无评论

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Sun, Geng Xiao, Jian Li, Jiahui Wang, Jiacheng Kang, Jiawen Niyato, Dusit Mao, Shiwen the College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China the College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore the School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore the School of Automation Guangdong University of Technology Guangzhou510641 China the Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

—Unmanned aerial vehicles (UAVs) have emerged as the potential aerial base stations (BSs) to improve terrestrial communications. However, the limited onboard energy and antenna power of a UAV restrict its communication range and transmission capability. To address these limitations, this work employs collaborative beamforming through a UAV-enabled virtual antenna array to improve transmission performance from the UAV to terrestrial mobile users, under interference from non-associated BSs and dynamic channel conditions. Specifically, we introduce a memory-based random walk model to more accurately depict the mobility patterns of terrestrial mobile users. Following this, we formulate a multi-objective optimization problem (MOP) focused on maximizing the transmission rate while minimizing the flight energy consumption of the UAV swarm. Given the NP-hard nature of the formulated MOP and the highly dynamic environment, we transform this problem into a multi-objective Markov decision process and propose an improved evolutionary multi-objective reinforcement learning algorithm. Specifically, this algorithm introduces an evolutionary learning approach to obtain the approximate Pareto set for the formulated MOP. Moreover, the algorithm incorporates a long short-term memory network and hyper-sphere-based task selection method to discern the movement patterns of terrestrial mobile users and improve the diversity of the obtained Pareto set. Simulation results demonstrate that the proposed method effectively generates a diverse range of non-dominated policies and outperforms existing methods. Additional simulations demonstrate the scalability and robustness of the proposed CB-based method under different system parameters and various unexpected circumstances. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised 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：