检索结果-内蒙古大学图书馆

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Editing Large Language Models

On the Robustness of Editing Large Language Models

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Ma, Xinbei Ju, Tianjie Qiu, Jiyang Zhang, Zhuosheng Zhao, Hai Liu, Lifeng Wang, Yulong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Baichuan Intelligent Technology China

ISBN: (纸本)9798891761643

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language generation without retraining. However, the robustness of model editing remains an open question. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI. We focus on three key research questions. RQ1: Can edited LLMs behave consistently resembling communicative AI in realistic situations? RQ2: To what extent does the rephrasing of prompts lead LLMs to deviate from the edited knowledge memory? RQ3: Which knowledge features are correlated with the performance and robustness of editing? Our empirical studies uncover a substantial disparity between existing editing methods and the practical application of LLMs. On rephrased prompts that are flexible but common in realistic applications, the performance of editing experiences a significant decline. Further analysis shows that more popular knowledge is memorized better, easier to recall, and more challenging to edit effectively. © 2024 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

Single Block Encoder-Decoder Transformer Model for Multi-Step Traffic Flow Forecasting 6

Single Block Encoder-Decoder Transformer Model for Multi-Ste...

引用

6th IEEE Symposium on computers and Informatics, ISCI 2024

作者： Omar, Mas Yakub, Fitri Talip, Mohamad Sofian Abu Maslan, Mohd Nazmin Sinha, Vijay Kumar Muljono, Muljono Universiti Teknologi Malaysia Wee Laboratory Malaysia-Japan International Institute of Technology Kuala Lumpur Malaysia Universiti Teknologi Malaysia Malaysia-Japan International Institute of Technology Department of Electronic System Engineering Kuala Lumpur Malaysia University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur Malaysia Universiti Teknikal Malaysia Faculty of Industrial and Manufacturing Technology and Engineering Melaka Malaysia Chitkara University School of Engineering & Technology Department of Computer Science & Engineering Himachal Pradesh India Universitas Dian Nuswantoro Faculty of Computer Science Semarang Indonesia

ISBN: (纸本)9798350353853

Accurate traffic flow forecasting is crucial for managing and planning urban transportation systems. Despite the widespread use of sequence modelling models like Long Short-Term Memory (LSTM) for this purpose, the potential of Transformer models remains underexplored. This is particularly true for the simplest form of a single block encoder-decoder Transformer model, which can be finely tuned through optimised hyperparameters. This paper examines the performance of a singular horizon-step forecasting method for multi-step traffic flow forecasting using a proposed Single Block Encoder-Decoder Transformer model optimised with a Grid Search algorithm. Results demonstrate that this model can enhance forecasting accuracy compared to the state-of-the-art LSTM model typically used for multi-step forecasting. The model effectively captures long-range temporal dependencies within a single road traffic flow dataset. It was tested on hourly traffic flow data to forecast the next 24 hours for the I5-North freeway in California, sourced from the Caltrans Performance Measurement System. The optimal configuration included an embedding dimension of 32, a feed-forward dimension of 128, and 8 attention heads. Results show a significant improvement, with a 4.7% reduction in Root Mean Squared Error compared to an LSTM model with two hidden layers of 100 neurons each, showcasing the potential of Single Block Encoder-Decoder Transformer models for real-world traffic prediction applications. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning 39

Enhancing Long-and Short-Term Representations for Next POI R...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jiajie Sang, Yu Zhang, Peng-Fei Wang, Jiaan Qu, Jianfeng Li, Zhixu School of Computer Science and Technology Soochow University Suzhou China School of Artificial Intelligence and Computer Science Jiangnan University China School of Electrical Engineering and Computer Science University of Queensland Australia School of Information Renmin University of China Beijing China Renmin University of China Suzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China

ISBN: (纸本)157735897X

Next POI recommendation aids users in predicting their destinations of interest and plays an increasingly vital role in location-based social services. Recent works focus on analyzing both long-term and short-term interests in POI recommendation to gain a deeper understanding of user profiles. However, these methods for modeling long-term user's sequences primarily rely on the Transformer model, which functions as a low-pass filter, often leading to the loss of high-frequency information. Additionally, long-term and short-term sequences are typically modeled independently, with short-term sequences often defined solely by the most recent check-ins, overlooking their interactions and dependencies. Therefore, we propose Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning (FHCRec). FHCRec captures both high-frequency and low-frequency information in long-term sequences to model richer long-term user's preference representations. Moreover, it harnesses the characteristics of the short-term subsequences embedded within long-term sequences to enhance short-term preference characterization via local and global hierarchical contrastive learning, resulting in more personalized short-term preferences. The enhanced long-term and short-term preferences are integrated to improve model recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of our method. 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

A roadmap for the commercialization of perovskite light emitters (August, 10.1038/s41578-022-00459-4, 2022)

引用

NATURE REVIEWS MATERIALS 2022年第10期7卷 833-833页

作者： Han, Tae-Hee Jang, Kyung Yeon Dong, Yitong Friend, Richard H. Sargent, Edward H. Lee, Tae-Woo Division of Materials Science and Engineering Hanyang University Seoul Republic of Korea Department of Materials Science and Engineering Seoul National University Seoul Republic of Korea School of Chemical and Biological Engineering Institute of Engineering Research Research Institute of Advanced Materials Soft Foundry Seoul National University Seoul Republic of Korea Department of Electrical and Computer Engineering University of Toronto Toronto Ontario Canada Cavendish Laboratory University of Cambridge Cambridge UK

Metal halide perovskites (MHPs) possess advantageous optoelectronic properties, so perovskite emitters and perovskite light-emitting diodes (PeLEDs) are promising candidates for next-generation high-colour-purity displays and lighting applications. Within the past 5 years, the luminescence efficiency of MHP emitters and PeLEDs has increased rapidly. However, the industrial applications of perovskites are impeded by several technical bottlenecks, such as insufficient colour reproducibility, low operational stability, toxicity and limited large-scale production. In this Review, we survey the current status of MHP emitters and PeLEDs and provide a technical roadmap to highlight the goals and requirements for them to successfully enter the markets for vivid displays with high colour purity, augmented and virtual reality displays and general and special lighting. We also set out steps for future research in MHPs and their device applications.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

A Networked Competitive Multi-Virus SIR Model: Analysis and Observability

引用

IFAC-PapersOnLine 2022年第13期55卷 13-18页

作者： Ciyuan Zhang Sebin Gracy Tamer Başar Philip E. Paré Elmore Family School of Electrical and Computer Engineering at Purdue University School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Coordinated Science Laboratory University of Illinois Urbana-Champaign

This paper proposes a novel discrete-time multi-virus SIR (susceptible-infected-recovered) model that captures the spread of competing SIR epidemics over a population network. First, we provide a sufficient condition for the infection level of all the viruses over the networked model to converge to zero in exponential time. Second, we propose an observation model which captures the summation of all the viruses’ infection levels in each node, which represents the individuals who are infected by different viruses but share similar symptoms. We present a sufficient condition for the model to be locally observable. We propose a Luenberger observer for the system state estimation and show via simulations that the estimation error of the Luenberger observer converges to zero before the viruses die out.

关键词： Biological network epidemics dynamics

来源：评论

学校读者我要写书评

暂无评论

Transfer Task-Averaged Natural Gradient for Efficient Many-Task Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Li, Yanchi Gong, Wenyin Gu, Qiong China University of Geosciences School of Computer Wuhan430074 China Hubei University of Arts and Science School of Computer Engineering Xiangyang441053 China Hubei University of Arts and Science Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Xiangyang441053 China

With the increasing requirement for computational efficiency in evolutionary algorithms when tackling many optimization tasks concurrently, many-task optimization (MaTO) has gained much attention in recent years. It involves extracting and transferring the knowledge from successful search experiences across many tasks. As the number of tasks and variable scale grows in MaTO, the need for efficient knowledge transfer in evolutionary algorithms becomes indispensable. In this paper, we present a task-averaged natural gradient-assisted natural evolution strategy (TNG-NES) to deal with MaTO efficiently. The task-averaged natural gradient captures how a group of task distributions evolves, considering their overall trends of mean and covariance. This can accelerate the optimization process across all tasks by leveraging the evolutionary similarities among multiple task search distributions. Notably, TNG-NES exhibits linear computational complexity concerning the number of tasks for knowledge transfer. Additionally, to adaptively utilize task-averaged natural gradient for distribution evolution and mitigate negative transfer, we introduce a transfer adaptive control mechanism for TNG-NES. We conducted extensive experiments on CEC19-MaTO, WCCI22-MaTO, our proposed large-scale MaTO benchmark suite, and real-world applications. The results validate the effectiveness of TNG-NES, outperforming state-of-the-art MaTO algorithms. © 1997-2012 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Mechanism of Threshold Voltage Instability in Double Gate α-IGZO Nanosheet TFT under Bias and Temperature Stress

引用

IEEE Journal of the Electron Devices Society 2024年 12卷 464-471页

作者： Aslam, Muhammad Chang, Shu-Wei Chen, Yi-Ho Lee, Yao-Jen Li, Yiming Lee, Wen-Hsi Parallel and Scientific Computing Laboratory National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electrical Engineering National Cheng Kung University Tainan City701401 Taiwan Institute of Pioneer Semiconductor Innovation Industry Academic Innovation School National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan

Amorphous indium gallium zinc oxide (a-IGZO)-based thin film transistors (TFTs) are increasingly becoming popular because of their potential in futuristic applications, including CMOS technology. Given the demand for CMOS-compatible, ultra-scaled, reliable, and high-performing devices, we fabricate and analyze scaled-channel a-IGZO-TFTs with an optimal double-gate structure, a thin nanosheet-based channel, and an effective high- κ dielectric namely HfO2. The reliably reported double gate IGZO nanosheet TFTs (DG-IGZO-NS-TFTs) are tested under positive and negative bias stress at variant temperatures, and the resulting modulations are analyzed critically. The reported DG-IGZO-NSTFTs exhibit a negative side threshold voltage shift (Δ Vth) accompanied by an increase in Ion/Ion(0) under negative bias temperature stress (NBTS) at elevated temperatures, which indicates the presence of additional charges. An anomalous negative side shifting of the Vth is observed under positive bias temperature stress (PBTS), where diffused hydrogen atoms are identified as introducing excess n-type carriers into the channel and causing the observed Δ Vth. The spectroscopic analysis is performed to establish evidence for the assumed mechanisms, and the role of individual gates is investigated in the context of performance variance under temperature-bias stress. Moreover, the partial reversibility of the stress-induced degradation is experimentally established and methodically discussed. Overall, the reported results offer a comprehensive understanding of scaled-channel DG-NS-IGZO-TFTs, which help shape performance-enhancement strategies, control degradation mechanisms, and define appropriate application scenarios. © 2013 IEEE.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

User-centric Service Provision for Edge-assisted Mobile AR: A Digital Twin-based Approach

User-centric Service Provision for Edge-assisted Mobile AR: ...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Conghao Zhou Jie Gao Yixiang Liu Shisheng Hu Nan Cheng Xuemin Sherman Shen Department of Electrical and Computer Engineering University of Waterloo Canada School of Information Technology Carleton University Canada School of Computer Science and Technology Xidian University China School of Telecommunications Engineering State Key Laboratory of ISN Xidian University China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Future 6G networks are envisioned to support mobile augmented reality (MAR) applications and provide customized immersive experiences for users via advanced service provision. In this paper, we investigate user-centric service provision for edge-assisted MAR to support the timely camera frame uploading of an MAR device by optimizing the spectrum resource reservation. To address the challenge of non-stationary data traffic due to uncertain user movement and the complex camera frame uploading mechanism, we develop a digital twin (DT)based data-driven approach to user-centric service provision. Specifically, we first establish a hierarchical data model with well-defined data attributes to characterize the impact of the camera frame uploading mechanism on the user-specific data traffic. We then design an easy-to-use algorithm to adapt the data attributes used in traffic modeling to the non-stationary data traffic. We also derive a closed-form service provision solution tailored to data-driven traffic modeling with the consideration of potential modeling inaccuracies. Trace-driven simulation results demonstrate that our DT-based approach for user-centric service provision outperforms conventional approaches in terms of adaptivity and robustness.

关键词： 6G mobile communication Adaptation models Simulation Cameras Data models Robustness Digital twins

来源：评论

学校读者我要写书评

暂无评论

User-centric Service Provision for Edge-assisted Mobile AR: A Digital Twin-based Approach

arXiv

引用

arXiv 2024年

作者： Zhou, Conghao Gao, Jie Liu, Yixiang Hu, Shisheng Cheng, Nan Shen, Xuemin Department of Electrical and Computer Engineering University of Waterloo Canada School of Information Technology Carleton University Canada School of Computer Science and Technology Xidian University China School of Telecommunications Engineering The State Key Laboratory of ISN Xidian University China

关键词：

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：