检索结果-内蒙古大学图书馆

Knowledge As Not Only Justified True Beliefs in Vision

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of Computer Science and Artificial Intelligence Wuhan University of Technology Sanya Science and Education Innovation Park of Wuhan University of Technology the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data

来源：评论

学校读者我要写书评

暂无评论

Observer-based event-triggered formation tracking control for second-order multi-agent systems in constrained region

引用

science China(Information sciences) 2025年第2期68卷 151-169页

作者： Fenglan SUN Zhonghua XU Wei ZHU ■ KURTHS Key Lab of Intelligent Analysis and Decision on Complex Systems School of ScienceChongqing University of Posts and Telecommunications Key Lab of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of AutomationChongqing University of Posts and Telecommunications Department of Complexity Science Potsdam Institute for Climate Impact Research Institute of Physics Humboldt University of Berlin

In this paper, an event-triggered time-varying formation tracking control for a class of second-order nonlinear multiagent systems(MAS) operating within a constrained region is investigated. To mitigate the negative effects of external unknown disturbance, a novel disturbance observer with performance guarantees is proposed, enabling precise disturbance *** the artificial potential field(APF) method, a repulsive potential function is introduced to prevent inter-agent collisions as well as collisions with environmental obstacles. To reduce continuous communication and frequent system updates, a sliding mode technique is incorporated into the formation tracking controller, utilizing an event-triggered mechanism. The controller is also applicable to the formation control of MAS in switching-constrained regions. The achievement of the specified timevarying geometric formation is rigorously demonstrated through the Lyapunov framework. Numerical simulations are presented to validate the effectiveness of the theoretical results.

关键词： formation tracking control region constraints repulsive potential function event-triggered mechanism

来源：评论

学校读者我要写书评

暂无评论

Building intelligence identification system via large language model watermarking: a survey and beyond

引用

Artificial intelligence Review 2025年第8期58卷 1-58页

作者： Wang, Xuhong Jiang, Haoyu Yu, Yi Yu, Jingru Lin, Yilun Yi, Ping Wang, Yingchun Qiao, Yu Li, Li Wang, Fei-Yue Shanghai Artificial Intelligence Laboratory Shanghai200433 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Automation BNRist Tsinghua University Beijing100084 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem. © The Author(s) 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models 31

SKIntern: Internalizing Symbolic Knowledge for Distilling Be...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liao, Huanxuan He, Shizhu Hao, Yupu Li, Xiang Zhang, Yuanzhe Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China National Science Library Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761964

Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using Chains of Thought (CoT) data distilled from LLMs, aiming to enhance their reasoning ability. Furthermore, Some CoT distillation methods introduce external symbolic knowledge into the generation process to improve the limited knowledge memory, reasoning ability and out-of-domain (OOD) generalization of SLMs. However, the introduction of symbolic knowledge increases computational overhead and introduces potential noise. In this paper, we introduce SKIntern, an innovative approach that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process, guided by a predefined linear decay schedule under curriculum learning. By efficiently internalizing knowledge, SKIntern reduces computational overhead and speeds up the reasoning process by focusing solely on the question during inference. It outperforms state-of-the-art baselines by over 5%, while reducing inference costs (measured in FLOPs) by up to 4× across a wide range of SLMs in both in-domain (ID) and out-of-domain (OOD) tasks. Our code will be available at https://***/Xnhyacinth/SKIntern. © 2025 Association for Computational Linguistics.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Robust Practical Stabilization for complex Dynamical Networks With DoS Attacks and Actuator Saturation

引用

IEEE Transactions on systems, Man, and Cybernetics: systems 2025年第5期55卷 3108-3118页

作者： Shi, Xueya Peng, Zhinan Yu, Junzhi Li, Hongfei Southwest University College of Electronic and Information Engineering Chongqing400715 China Sichuan Artificial Intelligence Research Institute Yibin644000 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

This article addresses the problem of designing an attack-resilient adaptive event-triggered (AET) controller for complex dynamical networks (CDNs) under DoS attacks and actuator saturation, with a focus on robust practical stability (RPS). First, considering the impact of DoS attacks on closed-loop systems, an AET controller against DoS attacks is designed. Unlike other event-triggered controllers, the complete timeline is divided, and the AET controller is built with two switching modes based on the intervals of dormant and active periods of DoS attacks in which the system is located. Second, to reconcile AET controller with actuator saturation, a switched system modeling approach is established that explicitly incorporates saturation constraints into the coupled network dynamics. Third, a switched Lyapunov-Krasovskii functional (LKF) is proposed, with which sufficient conditions are provided to ensured the RPS, and a joint design strategy is developed for the desired triggered matrix and feedback gain using linear matrix inequalities (LMIs). Moreover, the results are generalized to the case of actuator faults, indicating that the system is able to achieve RPS with actuator faults. Finally, the proposed method is verified through an example. © 2013 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of a Series-Parallel Self-Aligning Index Finger Exoskeleton

引用

IEEE Robotics and automation Letters 2025年第6期10卷 6456-6463页

作者： Sun, Ning Wang, Zelong Cheng, Long Li, Houcheng Niu, Ben Sun, Xijin Li, Ke Shandong Normal University School of Information Science and Engineering Jinan China Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing China Shandong University Institute of Intelligent Medical Engineering School of Control Science and Engineering Jinan China

Hand exoskeletons have become increasingly crucial for the rehabilitation of hand function, as relevant studies have shown that using the exoskeletons to assist in rehabilitation training can improve hand motor function. However, developing a human-robot kinematic compatibility exoskeleton while providing sufficient assistance torque is still a challenge. This paper develops a series-parallel self-aligning index finger exoskeleton to assist the index finger in flexion/extension and adduction/abduction training. A series-parallel mechanism driven by two motors simultaneously was proposed for the metacarpophalangeal (MCP) joint, which can ensure human-robot joint axes self-alignment and increase the joint assistance torque. A kinematic compatibility analysis method was proposed, and the kinematic compatibility of the series-parallel mechanism was analyzed. The degrees of freedom and forward kinematics of the proposed mechanism were analyzed, and its workspace was calculated, which results show that the motion range of the MCP joint can meet the grasping training requirements. Preliminary experiments were carried out, and the results indicate that the motion trajectory coefficients of the marker points at the MCP, PIP, and DIP joints averaged for all subjects with and without the proposed exoskeleton are 0.993, 0.956, and 0.939, respectively, which can verify the kinematic transparency of the proposed mechanism. The assistance torque generated by the proposed mechanism on the MCP joint can meet the joint assistance torque requirements. In a word, the proposed exoskeleton can achieve flexion/extension and adduction/abduction training, human-robot joint axes self-alignment, and provide sufficient assistance torque. © 2016 IEEE.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Learn-Gen-Plan: Bridging the Gap between Vision Language Models and Real-world Long-horizon Dexterous Manipulations

引用

IEEE Transactions on automation science and Engineering 2025年 22卷 15638-15649页

作者： Hao, Peng Cui, Shaowei Wei, Junhang Lu, Tao Cai, Yinghao Wang, Shuo Samsung R&D Institute China-Beijing Beijing100028 China Institute of Automation Beijing100190 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Chinese Academy of Sciences Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Beijing100190 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

Long-horizon dexterous tasks have been a long-standing problem in robotic manipulation. Previous studies have developed task and motion planning, imitation learning, and reinforcement learning methods for long-horizon manipulations. However, these methods are hard to achieve efficient planning for new tasks. Empowered with the Vision Language Model (VLM), recent studies significantly improve the generalization of robot systems. However, these works are only verified in simple pick-and-place tasks due to limited skills. To this end, we propose the Learn-Gen-Plan (LGP), which combines the VLM and learning-based primitives to endow robots with the ability to efficiently plan and complete various long-horizon dexterous tasks. LGP contains two key phases: skill generation and task planning. In skill generation, the Skill Generator is proposed to utilize the learned key primitives and hand-crafted trivial primitives to generate adaptive robot skills. In task planning, the Multimodal Planner generates the robot plan based on image observation, generated skills, and text prompts. We set up a series of dexterous tasks (e.g., cable routing, peg-in-hole assembly) in a real-world lighting circuit wiring scenario to evaluate LGP. The experimental results show that LGP efficiently generates robot plans with learned skills, controlling the robot to complete various multi-step cable wiring tasks. © 2004-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement

arXiv

引用

arXiv 2025年

作者： Yuan, Xiaowei Yang, Zhao Huang, Ziyang Wang, Yequan Fan, Siqi Ju, Yiming Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Beijing Academy of Artificial Intelligence China Meituan China University of Electronic Science and Technology of China China

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet they often struggle with context-faithfulness generations that properly reflect contextual knowledge. While existing approaches focus on enhancing the decoding strategies, they ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states. As a result, LLMs remain limited in their ability to fully leverage contextual knowledge. In this paper, we propose Context-aware Layer Enhancement (CaLE), a novel intervention method that enhances the utilization of contextual knowledge within LLMs’ internal representations. By employing V-usable information analysis, CaLE strategically amplifies the growth of contextual information at an optimal layer, thereby enriching representations in the final layer. Our experiments demonstrate that CaLE effectively improves context-faithful generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolutionary neural architecture search for automatically designing CNN-GRU-Attention neural networks for turntable servo systems

引用

Expert systems with Applications 2025年 283卷

作者： Xie, Cheng Xue, Bing Yang, Mingyi Zhang, Mengjie Xu, Zhigang Wang, Junyi Chen, Songlin Liu, Yang Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110169 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand University of Chinese Academy of Sciences Beijing101408 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Heilongjiang Harbin150001 China

Turntable servo systems are important experimental devices utilized in the semi-physical simulation and testing of aircraft. Building a model for turntable servo systems, which can accurately predict their operating states or behaviors, is important for the development and debugging of the whole servo control system. However, servo systems usually have complex nonlinear characteristics and external disturbances, which brings challenges to the accurate modeling of them. Therefore, this paper develops a modeling method for turntable servo systems by using CNN-GRU-Attention hybrid neural network models. The CNN-GRU-Attention model is used for compensating the nonlinear terms of the known dynamics model, thus effectively improving the modeling accuracy. Considering the complex architectures of the above hybrid model, an evolutionary neural architecture search (ENAS) algorithm is proposed accordingly, which can automatically design the architecture of the CNN-GRU-Attention models. During the designing process, a variable-length encoding strategy is proposed to represent the possible architectures, and novel crossover and mutation operators are proposed accordingly for the evolution of individuals. In addition, the real-time constraints are considered in the design of the search space, so that all the searched models can meet the real-time requirements. The experimental results show the CNN-GRU-Attention models obtained by the proposed ENAS algorithm achieve superior prediction performance over the peer competitors in most tasks. The effectiveness of the proposed method is further verified by analyzing the convergence and the search results. © 2025

关键词： Synchros

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：