检索结果-内蒙古大学图书馆

CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xinbei Zhang, Zhuosheng Zhao, Hai 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

Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GUI perception through different aspects and granularity, including screenshots and complementary detailed layouts for the visual channel and historical actions for the textual channel. Second, CAP decomposes the action prediction into sub-problems: action type prediction and action target conditioned on the action type. With our technical design, our agent achieves new state-of-the-art performance on AITW and META-GUI benchmarks, showing promising abilities in realistic scenarios. Code is available at https://***/xbmxb/CoCo-Agent. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphical user interfaces

A Survey on Federated Learning Poisoning Attacks and Defenses

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liang, Junchuan Wang, Rong Feng, Chaosheng Chang, Chin-Chen School of Computer Science Sichuan Normal University Chengdu China Visual Computing and Virtual Reality Key Laboratory of Sichuan Sichuan Normal University Chengdu China Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan

As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos, federated learning has received increasing attention in many fields, including finance, healthcare, and education. However, the invisibility of clients’ training data and the local training process result in some security issues. Recently, many works have been proposed to research the security attacks and defenses in federated learning, but there has been no special survey on poisoning attacks on federated learning and the corresponding defenses. In this paper, we investigate the most advanced schemes of federated learning poisoning attacks and defenses and point out the future directions in these areas. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning systems

Harnessing Large Vision and Language Models in Agriculture: A Review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongyan Qin, Shuai Su, Min Lin, Chengzhi Li, Anjie Gao, Junfeng Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin China Education Department of Guangxi Zhuang Autonomous Region Guilin China Department of Computer Science University of Aberdeen United Kingdom

Large models can play important roles in many domains. Agriculture is another key factor affecting the lives of people around the world. It provides food, fabric, and coal for humanity. However, facing many challenges such as pests and diseases, soil degradation, global warming, and food security, how to steadily increase the yield in the agricultural sector is a problem that humans still need to solve. Large models can help farmers improve production efficiency and harvest by detecting a series of agricultural production tasks such as pests and diseases, soil quality, and seed quality. It can also help farmers make wise decisions through a variety of information, such as images, text, etc. Herein, we delve into the potential applications of large models in agriculture, from large language model (LLM) and large vision model (LVM) to large vision-language models (LVLM). After gaining a deeper understanding of multimodal large language models (MLLM), it can be recognized that problems such as agricultural image processing, agricultural question answering systems, and agricultural machine automation can all be solved by large models. Large models have great potential in the field of agriculture. We outline the current applications of agricultural large models, and aims to emphasize the importance of large models in the domain of agriculture. In the end, we envisage a future in which famers use MLLM to accomplish many tasks in agriculture, which can greatly improve agricultural production efficiency and yield. © 2024, CC BY.

关键词： Fertilizers

GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hanyue Yang, Zhiliu Zuo, Xinhe Tong, Yuxin Long, Ying Liu, Chen School of Information Science and Engineering Yunnan University Yunnan Kunming650500 China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Yunnan Kunming650500 China Department of Electrical and Computer Engineering Clarkson University PotsdamNY13699 United States

This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) and aims to address the scalability and accuracy challenges faced by existing methods. For tackling the scalability issue, we split the large scene into multiple cells, and the candidate point-cloud and camera views of each cell are correlated through a visibility-based camera selection and a progressive point-cloud extension. To reinforce the rendering quality, three highlighted improvements are made in comparison with vanilla 3DGS, which are a strategy of the ray-Gaussian intersection and the novel Gaussians density control for learning efficiency, an appearance decoupling module based on ConvKAN network to solve uneven lighting conditions in large-scale scenes, and a refined final loss with the color loss, the depth distortion loss, and the normal consistency loss. Finally, the seamless stitching procedure is executed to merge the individual Gaussian radiance field for novel view synthesis across different cells. Evaluation of Mill19, Urban3D, and MatrixCity datasets shows that our method consistently generates more high-fidelity rendering results than state-of-the-art methods of large-scale scene reconstruction. We further validate the generalizability of the proposed approach by rendering on self-collected video clips recorded by a commercial drone. © 2024, CC BY.

关键词： 3D reconstruction

Kalman-based Adaptive Moment Estimation Optimisation Algorithm to Enhance GPT in LLMs for Medical Sentiment Analysis of Patient Health-related Feedback

学校读者我要写书评

暂无评论

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Chen, Xingchi Ma, Wenxin Li, Dazhou Zhu, Fa Routray, Sidheswar Guduri, Manisha Margala, Martin The Pengcheng Laboratory Shenzhen518000 China The College of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China The College of Information Science and Technology College of Artificial Intelligence Nanjing Forestry University Nanjing China The Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India The School of Computing and Informatics University of Louisiana LafayetteLA70503 United States

The progress in Natural Language Processing (NLP) using Large Language Models (LLMs) has greatly improved medical sentiment analysis of patient feedback extraction from health-related question and answer. However, using LLMs to analyze such data often requires significant training data and computational resources, resulting in considerable increases in training costs and durations, which is one of the primary issues in applying LLMs to real-world healthcare scenarios. To tackle these challenges, a novel optimization algorithm named KAdamEnGPT4LLM, based on Kalman filters and Adaptive Moment Estimation, is proposed to enhance training efficiency and reduce training costs of LLMs for analyzing patient feedback sentiment. Furthermore, the optimization algorithm KAdam-EnGPT4LLM is employed in training the LLM model GPT4ALL for medical sentiment analysis, resulting in the development of GPT4ALLMediSentAly-KAdam, which leds to faster convergence and more stable training specifically for medical questions and answer in the context of healthcare. The results show that our GPT4ALLMediSentAly-KAdam with the optimization algorithm KAdamEnGPT4LLM achieved better performance that include the best Accuracy, Recall, F1-score, and Runtime for both datasets, outperforming traditional fine-tuned LLMs such as the classic GPT4ALL, Ada, Babbage, Curie, and Duvinci. © 2013 IEEE.

关键词： Adaptive filters

Deep Graph Reinforcement Learning for UAV-Enabled Multi-User Secure Communications

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile computing 2025年

作者： Tang, Xiao Zhao, Kexin Shen, Chao Du, Qinghe Wang, Yichen Niyato, Dusit Han, Zhu Research & Development Institute Northwestern Polytechnical University Shenzhen518063 China National Key Laboratory of Wireless Communications Chengdu611731 China State Key Laboratory of Intelligent Game Taicang215400 China Northwestern Polytechinical University School of Electronics and Information Xi'an710072 China Xi'an Jiaotong University Faculty of Electronics and Information Engineering Xi'an710049 China Nanyang Technological University College of Computing and Data Science Singapore University of Houston Department of Electrical and Computer Engineering Houston77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging. The conventional approaches extended from optimization perspectives are usually quite involved, especially when jointly considering factors in different scales such as deployment and transmission in UAV-related scenarios. In this paper, we address the UAV-enabled multi-user secure communications by proposing a deep graph reinforcement learning framework. Specifically, we reinterpret the security beamforming as a graph neural network (GNN) learning task, where mutual interference among users is managed through the message-passing mechanism. Then, the UAV deployment is obtained through soft actor-critic reinforcement learning, where the GNN-based security beamforming is exploited to guide the deployment strategy update. Simulation results demonstrate that the proposed approach achieves near-optimal security performance and significantly enhances the efficiency of strategy determination. Moreover, the deep graph reinforcement learning framework offers a scalable solution, adaptable to various network scenarios and configurations, establishing a robust basis for information security in UAV-enabled communications. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

Designing of a Solar MPPT Controller with the Technique of Differentiation Between Uniform Irradiance and Partial Shading Conditions 9

学校读者我要写书评

暂无评论

Designing of a Solar MPPT Controller with the Technique of D...

9th IEEE International Conference on Power and Energy, PECon 2022

作者： Ahmed, Sajib Mekhilef, Saad Mubin, Marizan Tey, Kok Soon Rawa, Muhyaddin University of Malaya Power Electronics and Renewable Energy Research Laboratory Faculty of Engineering Department of Electrical Engineering Kuala Lumpur50603 Malaysia School of Science Computing and Engineering Technologies Swinburne University of Technology HawthornVIC3122 Australia University of Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia King Abdulaziz University Center of Research Excellence in Renewable Energy and Power Systems Jeddah21589 Saudi Arabia

ISBN: (数字)9781665409902

ISBN: (纸本)9781665409902

Solar energy is considered one of the best essential energy sources to solve the present power crisis. The solar photovoltaic system has a low conversion efficiency that inflicts maximum power extractions. The non-linear relationship between the voltage and current insists on using a maximum power point tracking (MPPT) controller. Perturb and observe (P&O) MPPT controller is popular because of its simple design and cost-effectiveness features;nonetheless, it has drawbacks while operating under partial shading conditions (PSC). The maximum power trapezium (MPT) method modified the P&O algorithm by incorporating an appropriate scanning mechanism for PSC. Despite having good PSC performance, this method's tracking time is much longer than the conventional algorithm in both uniform irradiance conditions (UIC) and PSC. The algorithm proposed in this paper modifies the MPT method with an extra strategy to distinguish between the UIC and PSC. If the pattern is recognized as UIC, the proposed method utilizes the conventional P&O algorithm to track the MPP;otherwise, scanning techniques are being used. The proposed algorithm's operation was tested on simulation using distinct UIC and PSC patterns and worked effectively. © 2022 IEEE.

关键词： Cost effectiveness

Preparing a commercial quantum key distribution system for certification against implementation loopholes

学校读者我要写书评

暂无评论

Physical Review Applied 2024年第4期22卷 044076页

作者： Vadim Makarov Alexey Abrikosov Poompong Chaiwongkhot Aleksey K. Fedorov Anqi Huang Evgeny Kiktenko Mikhail Petrov Anastasiya Ponosova Daria Ruzhitskaya Andrey Tayduganov Daniil Trefilov Konstantin Zaitsev Skolkovo Moscow 121205 Russia Vigo Quantum Communication Center NTI Center for Quantum Communications Department of Physics Faculty of Science Institute for Quantum Computing Department of Physics and Astronomy Quantum technology foundation (Thailand) Bangkok 10110 Thailand QRate Skolkovo Moscow 143026 Russia Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology Moscow 119991 Russia atlanTTic Research Center School of Telecommunication Engineering Department of Signal Theory and Communications Moscow 101000 Russia

A commercial quantum key distribution (QKD) system needs to be formally certified to enable its wide deployment. The certification should include the system’s robustness against known implementation loopholes and attacks that exploit them. Here we ready a fiber-optic QKD system for this procedure. The system has a prepare-and-measure scheme with decoy-state BB84 protocol, polarization encoding, a qubit source rate of 312.5 MHz, and is manufactured by QRate. We detail its hardware and postprocessing. We analyze the hardware for known implementation loopholes, search for possible new loopholes, and discuss countermeasures. We then amend the system design to address the highest-risk loopholes identified. We also work out technical requirements on the certification lab and outline its possible structure.

关键词： Quantum communication Quantum cryptography Quantum protocols

Blockchain-assisted Puncturable Signcryption for Cloud and Fog-Hosted Industrial Cyber-Physical Systems

学校读者我要写书评

暂无评论

IEEE Network 2025年

作者： Ma, Qingru Shen, Jian Pandi, Vijayakumar Gupta, Brij B. Arya, Varsha Mahalinghum, Maheswari Zhejiang Sci-Tech University School of Computer Science and Technology School of Artificial Intelligence Hangzhou310018 China Zhejiang Sci-Tech University School of Information Science and Engineering School of Cyber Science and Technology Zhejiang Key Laboratory of Digital Fashion and Data Governance Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Hangzhou310018 China Department of Computer Science and Engineering Tamil Nadu Tiruchirappalli620009 India Asia University Department of Computer Science and Information Engineering Taichung413 Taiwan China Medical University Hospital China Medical University Department of Medical Research Taichung Taiwan Pune412115 India School of Cybersecurity Korea University Seoul Korea Republic of Kyung Hee University Seoul02447 Korea Republic of Lebanese American University Beirut1102 Lebanon Center for Interdisciplinary Research Dehradun India Sathyabama Institute of Science and Technology School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai India

The widespread adoption of emerging technologies, such as interconnected sensors and advanced automation systems, has led to rapid advancements in smart industrial environments. While industrial cyber-physical systems (ICPSs) bring efficiency and innovation to industrial processes, the security risks are also of great concern. The existing work provides many methods for data security and authentication for ICPSs. However, since the authentication status of ICPSs is changeable, the up-to-date methods can hardly meet the requirements for rapid authentication and secure data transmission. What’s more, largescale message revocation incurs significant communication and computational costs. This paper proposes a blockchain-assisted identity-based puncturable signcryption (BC-IBPSC) scheme for cloud and fog-hosted ICPSs. First, based on the concepts of puncturable encryption and signature, a novel identity-based puncturable signcryption method is presented to achieve efficient verifiable data encryption. Second, the blockchain is utilized to record all valid and punctured messages, to achieve evidence storage and traceability. The results of the analysis indicate that the scheme ensures security and operates efficiently. In addition, experiments show that the size of the signcrypted files does not affect the value of Gas consumption on the blockchain when uploading proofs. © 2025 IEEE. All rights reserved.

关键词： Authentication