检索结果-内蒙古大学图书馆

29th International Conference on Computational Linguistics, COLING 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Bao, Changcun Chen, Huang Ren, Bo Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent Youtu Lab China

The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in later works. Different from existing methods, which mainly consider the pairwise relations between the text embedding and the corresponding fixed one-hot class label (data-to-class relations), this paper proposes a novel Contrastive Category Generative Adversarial Net (CoCGAN) to incorporate contrastive learning into adversarial category text generation, considering more flexible data-to-class relations as well as relations between the multiple text embeddings in the same batch (data-to-data relations). The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples. Accordingly, the generator tries to produce more realistic samples which can confuse the discriminator. Experimental results on both synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generation models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Time-sequential color code division multiplexing holographic display with metasurface

引用

Opto-Electronic Advances 2023年第8期6卷 8-16页

作者： Xin Li Qinmiao Chen Xue Zhang Ruizhe Zhao Shumin Xiao Yongtian Wang Lingling Huang Beijing Engineering Research Center of Mixed Reality and Advanced Display School of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China MoE Key Laboratory of Photoelectronic Imaging Technology and System and MIIT Key Laboratory of Photonics Information TechnologySchool of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China State Key Laboratory on Tunable Laser Technology Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information SystemHarbin Institute of Technology(Shenzhen)Shenzhen 518055China National Key Laboratory of Science and Technology on Advanced Composites in Special Environments Harbin Institute of TechnologyHarbin 150080China Collaborative Innovation Center of Extreme Optics Shanxi UniversityTaiyuan 030006China

Color metasurface holograms are powerful and versatile platforms for modulating the amplitude,phase,polarization,and other properties of light at multiple operating ***,the current color metasurface holography can only realize static *** this study,we propose and demonstrate a multiplexing metasurface technique combined with multiwavelength code-division multiplexing(CDM)to realize dynamic *** code references are utilized to record information within a single metasurface and increase the information capacity and security for anticracks.A total of 48 monochrome images consisting of pure color characters and multilevel color video frames were reconstructed in dual polarization channels of the birefringent metasurface to exhibit high information density,and a video was displayed via sequential illumination of the corresponding code patterns to verify the ability of dynamic *** approach demonstrates significant application potential in optical data storage,optical encryption,multiwavelengthversatile diffractive optical elements,and stimulated emission depletion microscopy.

关键词： metasurface color holography dynamic display code division multiplexing

来源：评论

学校读者我要写书评

暂无评论

AMOR: a recipe for building adaptable modular knowledge agents through process feedback 24

AMOR: a recipe for building adaptable modular knowledge agen...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Jian Guan Wei Wu Zujie Wen Peng Xu Hongning Wang Minlie Huang The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China and Ant Group Ant Group The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798331314385

The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process. AMOR builds reasoning logic over a finite state machine (FSM) that solves problems through autonomous executions and transitions over disentangled modules. This allows humans to provide direct feedback to the individual modules, and thus naturally forms process supervision. Based on this reasoning and feedback framework, we develop AMOR through two-stage fine-tuning: warm-up and adaptation. The former fine-tunes the LLM with examples automatically constructed from various public datasets, enabling AMoR to generalize across different knowledge environments, while the latter tailors AMOR to specific domains using process feedback. Extensive experiments across multiple domains demonstrate the advantage of AMoR to strong baselines, thanks to its FSM-based reasoning and process feedback mechanism. The code and data are publicly available at https://***/JianGuanTHU/AMOR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Variable-Curvature Kinematic Modeling of a New Segmented Flexible Assistive Hand Exoskeleton

Design and Variable-Curvature Kinematic Modeling of a New Se...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Zhang, Can Li, Guotao Li, Xiong Cheng, Long China University of Mining and Technology-Beijing School of Mechanical Electronic and Information Engineering Beijing100083 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China Technology Co. Ltd. RoboticsX Lab China

ISBN: (纸本)9798350325706

Robotic hand exoskeletons can assist patients with hand disabilities and the elderly to perform their activities of daily living (ADL). However, designing a segmented variable curvature flexible hand exoskeleton robot is still a great challenge. In this paper, a wearable flexible finger exoskeleton based on a double-layer parallel flat spring structure is first proposed by designing different widths of the segments of the fixed-length flat springs, which can achieve different curvatures. Second, a variable curvature kinematic model based on the relative displacement is established and analyzed. Third, a variable curvature kinematic model based on the push force is established and analyzed considering the effects of friction and external forces. The curvature value of each segment is obtained by recursively calculating the forces and moments of each segment. Finally, it is verified by experiments that the variable curvature kinematic model with friction is more accurate than the variable curvature kinematic model without friction. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Gaussian Filtering for Nonlinear Dynamic systems Using Variational Inference 27

On the Gaussian Filtering for Nonlinear Dynamic Systems Usin...

引用

27th International Conference on Information Fusion, FUSION 2024

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Li, Ji University of Canterbury Department of Electrical and Computer Engineering Christchurch New Zealand National University of Defense Technology State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems Changsha China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Locaris Electronic Technology Co. Ltd Zhengzhou China

ISBN: (纸本)9781737749769

This paper introduces a new variational Gaussian filtering approach for estimating the state of a nonlinear dynamic system. We first assume that the predictive distribution of the state is Gaussian and derive an iterative method for updating the state posterior in the natural parameter space through KullbackLeibler divergence minimization. The obtained update rule is the same as that of the conjugate-computation variational inference technique in Bayesian learning. The derivation here is simpler and more insightful. We then impose a Wishart prior on the inverse of the state prediction covariance to take into account the impact of approximating the state predictive distribution using a Gaussian density on the state posterior estimation. The prediction covariance is identified jointly with the state using variational inference and the established state posterior update rule to achieve the desired Gaussian filtering. Simulation study examines the performance of the proposed filtering framework in target tracking based on bearing and range measurements. © 2024 ISIF.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Double Side Interfacial Optimization for Low-Temperature Stable CsPbI_(2)Br Perovskite Solar Cells with High Efficiency Beyond 16%

引用

Energy & Environmental Materials 2022年第2期5卷 637-644页

作者： Jing Ma Jie Su Zhenhua Lin Jian He Long Zhou Tao Li Jincheng Zhang Shengzhong Liu Jingjing Chang Yue Hao State Key Discipline Laboratory of Wide Band Gap Semiconductor Technology Shaanxi Joint Key Laboratory of GrapheneSchool of MicroelectronicsXidian UniversityXi’an 710071China Advanced Interdisciplinary Research Center for Flexible Electronics Xidian UniversityXi’an 710071China Centre for Spintronics and Quantum System State Key Laboratory for Mechanical Behavior of MaterialsSchool of Materials Science and EngineeringXi’an Jiaotong UniversityXi’an 710049China Key Laboratory of Applied Surface and Colloid Chemistry National Ministry of Education Shaanxi Engineering Lab for Advanced Energy TechnologySchool of Materials Science and EngineeringShaanxi Normal UniversityXi’an 710119China

CsPbI_(2)Br perovskite solar cells have achieved rapid development owing to their exceptional optoelectronic properties and relatively outstanding ***,open-circuit voltage(Voc)loss caused by band mismatch and charge recombination between perovskite and charge transporting layer is one of the crucial obstacles to further improve the device ***,we proposed a bilayer electron transport layer ZnO(bottom)/SnO_(2)(top)to reduce the Voc loss(Eloss)and promote device Voc by ZnO insert layer thickness modulation,which could improve the efficiency of charge carrier extraction/transfer and suppress the charge carrier *** addition,guanidinium iodide top surface treatment is used to further reduce the trap density,stabilize the perovskite film and align the energy levels,which promotes the fill factor,short-circuit current density(Jsc),and stability of the *** a result,the champion cell of double-side optimized CsPbI_(2)Br perovskite solar cells exhibits an extraordinary efficiency of 16.25%with the best Voc as high as 1.27 V and excellent thermal and storage stability.

关键词： CsPbI_(2)Br dual interfacial optimization high performance low temperature perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

S-SIFT: A Simple SIFT Algorithm with High Efficiency

S-SIFT: A Simple SIFT Algorithm with High Efficiency

引用

International Conference on Solid-state and Integrated Circuit technology

作者： Yixue Wang Yujie Huang Liyuan Peng Mingyu Wang Wenhong Li Minge Jing Xiaoyang Zeng State Key Lab of ASIC & System Fudan University Shanghai China Shanghai ExploreX Technology Co. Ltd. Shanghai China

ISBN: (数字)9798350361834

ISBN: (纸本)9798350361841

Finding distinctions and connections between multiple visual targets through the detection of keypoints has become one of the research hot-spots in the field of computer vision. SIFT has received wide recognition and attention for its powerful performance in image match. However, the original SIFT has high complexity and time-consuming problems. In this paper, we propose Simple SIFT (S-SIFT), an improved SIFT algorithm in which the construction of Gaussian pyramid and the order of detection steps have been changed. Through the collaborative improvement and optimization on the scale space and algorithm framework, a more efficient local keypoints detecting method is achieved. Experiments demonstrat that SSIFT guarantees satisfactory accuracy with a significant reduction in the computational overhead. Meanwhile, S-SIFT is robust to common image deformations such as rotation, scale change and affine.

关键词： Integrated circuit technology Visualization Computer vision Image recognition Accuracy Deformation Collaboration Complexity theory Optimization

来源：评论

学校读者我要写书评

暂无评论

Conditional Cycle Termination RANSAC

Conditional Cycle Termination RANSAC

引用

International Conference on Solid-state and Integrated Circuit technology

作者： Tong Jiang Yujie Huang Liyuan Peng Mingyu Wang Wenhong Li Minge Jing Xiaoyang Zeng State Key Lab of ASIC & System Fudan University Shanghai China Shanghai ExploreX Technology Co. Ltd. Shanghai China

ISBN: (数字)9798350361834

ISBN: (纸本)9798350361841

In the field of computer vision, the acquired dataset usually contains a certain number of outliers and noise, which leads to errors in the estimated mathematical model. RANSAC estimates model parameters by randomly selecting a subset of the data, reducing the impact of these outliers and noise. However, for datasets with a high proportion of inliers, the traditional RANSAC has to perform a large number of cyclic modeling operations after finding the correct model. In this paper, a conditional termination verification strategy for RANSAC is presented. We boldly terminated the cycle operation early which reduced the amount of computation by 17.78% and increased the computation speed by 34.09%.

关键词： Integrated circuit technology Computer vision Computational modeling Noise Mathematical models Data models Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection and Fault Diagnosis Method for Autonomous Transport Vehicles on Unstructured Roads

Anomaly Detection and Fault Diagnosis Method for Autonomous ...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Yifang Zhang Guizhen Yu Han Li Chaoqi Zhang Lecong Li Chuanying Zhang State Key Lab of Intelligent Transportation System The Key Laboratory of Autonomous Transportation Technology for Special Vehicles Ministry of Industry and Information Technology Beihang University School of Transportation Science and Engineering Beijing China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Autonomous vehicles in mining areas undertake substantial production tasks and are prone to various faults during operation. Early detection of abnormalities, along with timely fault warnings and diagnoses, can enhance transportation safety and increase vehicle turnout rates. This study utilizes driving data from autonomous vehicles in mining areas and considers the characteristics of unstructured road scenes. The driving area is segmented into distinct intervals, and Kullback-Leibler (KL) divergence is applied within each interval to detect anomalies in the vehicle's lateral deviation during operation. Experimental results demonstrate that the proposed method achieves an anomaly detection accuracy of 91.4%, with a false negative rate of 8.3% and a false positive rate of 8.7%.

关键词： Fault diagnosis Accuracy Roads Transportation Production Safety Logic Anomaly detection Autonomous vehicles Standards

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Mechanism-Based MPC for Path-Tracking Control of Four-Wheel Steering Vehicles

Event-Triggered Mechanism-Based MPC for Path-Tracking Contro...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Xiangyu Zhang Guoyan Xu Han Li Peng Chen Qi Xia Han Cai State Key Lab of Intelligent Transportation System School of Transportation Science and Engineering The Key Laboratory of Autonomous Transportation Technology for Special Vehicles Ministry of Industry and Information Technology Beihang University Beijing China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

In this study, we tackle the path-tracking problem of a nonlinear four-wheel steering vehicle dynamics model subject to model mismatches and propose a model predictive control (MPC) algorithm based on an event-triggered mechanism (ET -MPC). The goal is to maintain closed-loop control performance while reducing the computational and communication burdens of traditional MPC. We introduce an ET -MPC framework utilizing a model-free reinforcement learning agent with proximal policy optimization (PPO). This agent interacts with the MPC system, progressively learning to determine the optimal event-triggered mechanism. To enhance exploration and training efficiency, we incorporate the Long Short-Term Memory (LSTM) technique into PPO. Experimental results show that the proposed ET -MPC framework, combined with reinforcement learning for reward optimization, demonstrates superior overall performance in path-tracking control of four-wheel steering vehicles.

关键词： Training Event detection Computational modeling Heuristic algorithms Predictive models Prediction algorithms Vehicle dynamics Long short term memory Frequency control Predictive control

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：