检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Xie, Yunfan Zou, Lixin Luo, Dan Tang, Min Li, Chenliang Dong, Liming Luo, Xiangyang Wuhan University Wuhan China Lehigh University Bethlehem United States Monash University Melbourne Australia National Defense University Beijing China State Key Lab of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9798891761964

Although large language models (LLMs) trained on extensive multilingual corpora exhibit impressive language transfer, they often fail to respond in the user's desired language due to corpus imbalances, an embarrassingly simple problem known as the language confusion. However, existing solutions like in-context learning and supervised fine-tuning (SFT) have drawbacks: in-context learning consumes context window space, diminishing attention as text lengthens, while SFT requires extensive, labor-intensive data collection. To overcome these limitations, we propose the language-sensitive intervention (LSI), a novel, lightweight, and label-free approach. Specifically, we analyze language confusion from a causal perspective, revealing that the training corpus's language distribution acts as a confounder, disadvantaging languages that are underrepresented in the dataset. Then, we identify a language-sensitive dimension in the LLM's residual stream, i.e., the language vector, which allows us to estimate the average causal effect of prompts on this dimension. During inference, we directly intervene on the language vector to generate responses in the desired *** further advance research on this issue, we introduce a new benchmark that detects language confusion and assesses content quality. Experimental results demonstrate that our method effectively mitigates language confusion without additional complex mechanisms. Our code is available at https://***/SoseloX/LSI. © 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

Boosting cationic and anionic redox activity of Li-rich layered oxide cathodes via Li/Ni disordered regulation

引用

Journal of Energy Chemistry 2025年第1期100卷 533-543页

作者： Zewen Liu Zhen Wu Hao Wang Xudong Zhang Yuanzhen Chen Yongning Liu Shengwu Guo Shenghua Chen Yanli Nan Yan Liu State Key Laboratory for Mechanical Behavior of Materials Xi’an Jiaotong UniversityXi’an 710049ShaanxiChina School of Materials Science and Engineering Xi’an University of Architecture and TechnologyXi’an 710055ShaanxiChina Hefei Advanced Computing Center Operation Management Corp Ltd Hefei 230088AnhuiChina Network Information Center Xi’an Jiaotong UniversityXi’an 710049ShaanxiChina

Lithium-rich layered oxides (LLOs) are increasingly recognized as promising cathode materials for nextgeneration high-energy-density lithium-ion batteries (LIBs).However,they suffer from voltage decay and low initial Coulombic efficiency (ICE) due to severe structural degradation caused by irreversible O ***,we introduce a three-in-one strategy of increasing Ni and Mn content,along with Li/Ni disordering and TM–O covalency regulation to boost cationic and anionic redox activity simultaneously and thus enhance the electrochemical activity of *** target material,Li_(1.2)Ni_(0.168)Mn_(0.558)Co_(0.074)O_(2)(L1),exhibits an improved ICE of 87.2%and specific capacity of 293.2 mA h g^(-1)and minimal voltage decay of less than 0.53 m V cycle-1over 300 cycles at 1C,compared to Li_(1.2)Ni_(0.13)Mn_(0.54)Co_(0.13)O_(2)(Ls)(274.4 mA h g^(-1)for initial capacity,73.8%for ICE and voltage decay of 0.84 mV/cycle over 300 cycles at 1C).Theoretical calculations reveal that the density of states (DOS) area near the Fermi energy level for L1 is larger than that of Ls,indicating higher anionic and cationic redox reactivity than ***,L1 exhibits increased O-vacancy formation energy due to higher Li/Ni disordering of 4.76%(quantified by X-ray diffraction Rietveld refinement) and enhanced TM–O covalency,making lattice O release more difficult and thus improving electrochemical *** increased Li/Ni disordering also leads to more Ni^(2+)presence in the Li layer,which acts as a pillar during Li+de-embedding,improving structural *** research not only presents a viable approach to designing low-Co LLOs with enhanced capacity and ICE but also contributes significantly to the fundamental understanding of structural regulation in high-performance LIB cathodes.

关键词： Low-Co Li-rich layered oxides Li/Ni disordering TM-O covalency Cationic and anionic redox activity

来源：评论

学校读者我要写书评

暂无评论

Stance Detection for Social Text: Inference-Enhanced Multi-Task Learning with Machine-Annotated Supervision

Stance Detection for Social Text: Inference-Enhanced Multi-T...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qiankun Pi Jicang Lu Yepeng Sun Qinlong Fan Xukun Zhou Shouxin Shang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China School of Information Renmin University of China Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Stance detection, a natural language processing technique, captures user attitudes on controversial social media topics. However, the semantic ambiguity of social texts makes accurate stance determination challenging. Existing annotated data is often domain-specific, resulting in poor model generalization for unseen targets and cross-domain scenarios. To tackle this challenge, we introduce inference tasks related to stance detection as auxiliary tasks and use a multitask learning approach to improve the model’s understanding of textual semantics. Meanwhile, to alleviate the scarcity of annotated data, we use argumentation corpus with abundant resources as the source domain to train the basic stance detection model. We integrate this model with a large-scale framework to facilitate weakly supervised learning for machine annotation of unlabeled social texts, thereby boosting the model’s adaptability across different targets and domains. Experimental results on four Twitter datasets demonstrate that our method can significantly improve the model’s stance discriminative ability and generalization performance.

关键词： Adaptation models Weak supervision Social networking (online) Annotations Semantics Blogs Transfer learning Signal processing Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Obtaining Electromagnetic Properties of Multi-Type Media in Realistic Environments:state-of-the-Art and Prospects

引用

china Communications 2025年第1期22卷 25-40页

作者： Guo Lantu Guan Ke Liu Ting He Danping Zhang Haixia Zhu Qiuming Lu Jun Zhang Minggao China Research Institute of Radiowave Propagation Qingdao 266107China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong UniversityBeijing 100044China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Control Science and Engineering Shandong UniversityJinan 250061China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Jinan 250061China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Jiaxing University Jiaxing 314001China

To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions that can break through the bottlenecks of current ***,based on the survey of three mainstream approaches for acquiring EM properties of media,we identify the difficulties when implementing them in realistic *** a focus on addressing these problems and challenges,we propose a novel paradigm for obtaining the EM properties of multi-type media in realistic ***,within this paradigm,we describe the implementation approach of the key technology,namely“multipath extraction using heterogeneous wave propagation data in multi-spectrum cases”.Finally,the latest measurement and simulation results show that the EM properties of multi-type media in realistic environments can be precisely and efficiently acquired by the methodology proposed in this study.

关键词： electromagnetic properties of media multi-type media parameter inversion ray tracing realistic environment

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

On the Cycle Structure of Some Nonlinear Feedback Shift Registers

引用

Chinese Journal of Electronics 2025年第4期23卷 801-804页

作者： Zhongxiao Wang Hong Xu Wenfeng Qi State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Information Science and Technology Institute Zhengzhou China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

In this paper, we partly determine the cycle structure of two types of Nonlinear feedback shift registers (NFSRs). Based on these results, the cycle structure of a class of NFSRs with symmetric feedback functions can be completely characterized. Furthermore, an alternative proof of Kjeldsen's results is presented. Compared with the original proof based on abstract algebra theory, ours is straightforward and easy to understand.

关键词： Abstract algebra Shift registers Cryptography

来源：评论

学校读者我要写书评

暂无评论

Robust Watermarking Based on Multi-layer Watermark Feature Fusion

引用

IEEE Transactions on Multimedia 2025年

作者： Wu, Shaowu Lu, Wei Luo, Xiangyang Sun Yat-Sen University School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450002 China

The purpose of robust image watermarking is to embed a watermark into a carrier image in an invisible form and extract the watermark successfully even under noise interference conditions to achieve copyright confirmation and traceability. Although watermarking methods based on deep learning can improve the robustness by adding a noise simulation layer, few theoretical analyses of the codec structure have been conducted. Theoretical explainability is the theoretical basis for developing a network architecture, which plays a guiding role in network development. On the basis of the interpretability of convolutional networks, this paper analyzes the mathematical process of embedding and extracting watermarks in codecs and proposes a novel watermarking framework based on multi-layer watermark feature fusion. Specifically, the encoder can be a convolutional network structure of arbitrary depth, whereas the decoder needs only to adopt its corresponding deconvolution structure. To improve the quality and robustness of the generated watermarked image, the watermark is associated with an arbitrary layer feature space in the decoder. In the decoder, the network quickly converges to each original encoding feature space through the deconvolution structure, thus decoupling the watermark features. Finally, the watermark is extracted via the automatic fusion of multi-layer watermark features. The experimental results show that the proposed method is suitable for few-shot learning, and its invisibility, robustness and generalization performance on multiple datasets are significantly better than those of other advanced methods. © 2025 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Triangle Matters! TopDyG: Topology-aware Transformer for Link Prediction on Dynamic Graphs 34

Triangle Matters! TopDyG: Topology-aware Transformer for Lin...

引用

34th ACM Web Conference, WWW 2025

作者： Zhang, Xin Cai, Fei Zheng, Jianming Pan, Zhiqiang Chen, Wanyu Chen, Honghui Chen, Chonghao National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China College of Electronic Countermeasures National University of Defense Technology Hefei China

ISBN: (纸本)9798400712746

Dynamic graph link prediction is widely utilized in the complex web of the real world, such as social networks, citation networks, recommendation systems, etc. Recent Transformer-based link prediction methods on dynamic graphs not only fail to model the fine-grained structures such as triangles with the vanilla Transformers in the graph serialization process, but also amplify the imbalanced distribution of graphs because of their over-estimation of high-degree nodes. To tackle these issues, we propose a Topology-aware Transformer on Dynamic Graph (TopDyG) for link prediction, consisting of a topology injected Transformer (Ti-Transformer) and a mutual information learning (Mi-Learning). The Ti-Transformer explores the explicit structure of serialized graphs, capturing the topological features. The Mi-Learning mines the relationship between nodes by modeling the mutual information with a prior knowledge, alleviating the over-estimation of high-degree nodes when applying the Transformer-based models for the dynamic graph link prediction task. Extensive experiments on four public datasets containing both transductive and inductive settings present the superiority of our proposal. In particular, TopDyG presents an improvement of 43.27% and 28.75% against the state-of-the-art baselines in terms of NDCG and Jaccard, respectively. The advantages are especially obvious on the high-density graphs. © 2025 Copyright held by the owner/author(s).

关键词： Dynamic graphs Link prediction Topology Transformer

来源：评论

学校读者我要写书评

暂无评论

Population-Based Meta-Heuristic Optimization Algorithm Booster: An Evolutionary and Learning Competition Scheme

引用

Neurocomputing 2025年 643卷

作者： Wang, Jun Dong, Junyu Zhou, Huiyu Dong, Xinghui State Key Laboratory of Physical Oceanography and Faculty of Information Science and Engineering Ocean University of China China School of Computing and Mathematical Sciences University of Leicester United Kingdom

In a Population-Based Meta-Heuristic Optimization Algorithm (PMOA), individuals in the population will constantly generate new promising individuals, to form new populations. Although the population continuously changes, the variations in each individual are traceable in most algorithms. An individual in the population comes from the individual in the previous population. The direction of the evolution of populations can be identified on top of this historical inheritance relationship, which improves the efficiency of PMOAs and solves optimization problems more effectively. Since Recurrent Neural Networks (RNNs) are able to capture the temporal dependencies in sequences, we are motivated to propose a novel but simple Evolutionary and Learning Competition Scheme (ELCS), also referred to as the PMOA Booster, in which individuals keep changing for the better fitness based on the heuristic rules of the PMOA while an RNN is used to learn the process that each individual changes in order to guide the generation of promising individuals. The ELCS automatically selects the RNN or PMOA which generates more individuals with the better fitness. We test the proposed scheme using the benchmark of IEEE Congress on Evolutionary Computation 2022 competition (CEC 2022). The results show that this scheme is able to boost the performance of both the classical and state-of-the-art PMOAs and outperforms its counterparts. Also, the ELCS produces promising results in two real-world industrial scenarios. We believe that the effectiveness of the proposed ELCS is due to the adaptive competition between the RNN and the PMOA. © 2025 Elsevier B.V.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

ThicknesVAE: Learning a Latera Prior for Clothed Human Body Reconsuction

ThicknesVAE: Learning a Latera Prior for Clothed Human Body ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Xiaotao Fan, Zhaoxin He, Huiguang Shen, Dinggang School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai201210 China NeuBCI Group State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Academy of Blockchain and Edge Computing China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200232 China Shanghai Clnical Research and Trial Center Shanghai201210 China

ISBN: (纸本)9798350368741

Sandwich-like structures have shown remarkable efficacy in clothed human reconstruction. However, these approaches often generate unrealistic side geometries due to inadequate handling of lateral regions. This paper addresses this limitation by incorporating the side geometry of clothed humans as a prior. We propose ThicknessVAE, a novel two-stage method that makes two key contributions: (1) We learn a prototype from point clouds for the lateral regions of clothed humans to extract common and detailed geometric features. (2) We utilize this prototype as a prior to transform geometric features into a thickness map associated with clothed human images, enabling refined normal integration for sandwich-like reconstruction methods. By seamlessly integrating our model into the sandwich-like reconstruction pipeline, we achieve highly realistic side views. Both qualitative and quantitative experiments demonstrate that our approach is comparable to state-of-the-art methods in terms of side-view realism. © 2025 IEEE.

关键词： 3D Human Reconsruction Normal Integraton Prior 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：