检索结果-内蒙古大学图书馆

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

network link weight optimization based on antisymmetric deep graph networks and reinforcement learning

Network link weight optimization based on antisymmetric deep...

引用

Next Generation Data-driven networks (NGDN), International Conference on

作者： Yuhan Chen Yingya Guo Department of Computer and Data Science Fuzhou University Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

Route optimization is a key core technology to optimize network traffic distribution, achieve network load balancing, and improve network performance. Traditional distributed networks widely run shortest-path based routing protocols, and the path of traffic is determined by the link weights of the distributed network, so routing optimization methods are usually optimized around the link weights of the network. Heuristics-based link weight optimization methods are widely used. However, heuristic methods rely on manually set rules, which are poorly generalized and cannot adapt well to dynamically changing traffic demands. Compared to heuristics, deep reinforcement learning (DRL) has the advantage of extracting more accurate feature representations in addition to its ability to handle high-dimensional state and action spaces. We propose a network link weight optimization method based on anti-symmetric deep graph networks (A-DGN) and reinforcement learning using a novel GNN framework anti-symmetric deep graph networks, where link weights are adjusted to reduce the network link utilization with the optimization objective of minimizing the maximum link utilization in the network. Experimental results show that the proposed method achieves significant performance improvements in the link weight optimization problem in four real-world network topology scenarios.

关键词： Measurement network topology Optimization methods Telecommunication traffic Feature extraction Deep reinforcement learning Routing Load management Routing protocols Next generation networking

来源：评论

学校读者我要写书评

暂无评论

DragEntity:Trajectory Guided Video Generation using Entity and Positional Relationships 24

DragEntity:Trajectory Guided Video Generation using Entity a...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wan, Zhang Tang, Sheng Wei, Jiawei Zhang, Ruize Cao, Juan Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Zhengzhou University Zhengzhou China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798400706868

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly, control conditions (such as depth maps, 3D Mesh) are difficult for ordinary users to obtain directly. Secondly, it's challenging to drive multiple objects through complex motions with multiple trajectories simultaneously. In this paper, we introduce DragEntity, a video generation model that utilizes entity representation for controlling the motion of multiple objects. Compared to previous methods, DragEntity offers two main advantages: 1) Our method is more user-friendly for interaction because it allows users to drag entities within the image rather than individual pixels. 2) We use entity representation to represent any object in the image, and multiple objects can maintain relative spatial relationships. Therefore, we allow multiple trajectories to control multiple objects in the image with different levels of complexity simultaneously. Our experiments validate the effectiveness of DragEntity, demonstrating its excellent performance in fine-grained control in video generation. © 2024 ACM.

关键词： controllable video generation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Particle Swarm Algorithm Based on Fitness Landscape information

An Enhanced Particle Swarm Algorithm Based on Fitness Landsc...

引用

Congress on Evolutionary Computation

作者： Zhenya Diao Fei Yu Jian Guan Meitong Liu Key Lab of Intelligent Optimization and Information Processing School of Physics and Information Engineering Minnan Normal University Zhangzhou China Key Laboratory of Light Field Manipulation and System Integration Applications in Fujian Province Key Lab of Intelligent Optimization and Information Processing School of Physics and Information Engineering Minnan Normal University Zhangzhou China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

In the original Particle Swarm Optimization (PSO), the selection of parameters significantly impacts the search capability of PSO. The paper introduces an innovative algorithm called Fitness Landscape-based PSO (FLPSO) to address the impact of parameter selection on the search capability of PSO. The algorithm focuses on acquiring fitness landscape information and analyzing the population state to intelligently select appropriate parameters in each generation. FLPSO defines four primary states: exploration, exploitation, convergence, and escaping state. In the convergence state, an elite learning strategy is incorporated to help the algorithm escape potential local optima by targeting the global best particle. To validate the efficacy of FLPSO, the paper conducted experiments on 30 different characteristic test functions from CEC2017. FLPSO was compared with six existing algorithms: PSO, PSO-TVAC, APSO, AWPSO, RPSO and ASRPPSO. The experimental results showed significant improvements in FLPSO, providing promising evidence for its effectiveness.

关键词： Sociology Particle swarm optimization Statistics Convergence

来源：评论

学校读者我要写书评

暂无评论

Event-triggered H∞ Consensus of Leader-follower Multi-agent Systems 43

Event-triggered H∞ Consensus of Leader-follower Multi-agent...

引用

43rd Chinese Control Conference, CCC 2024

作者： Gong, Cheng Ai, Chenguang Zuo, Xuemin Ma, Zhuang Dai, W. Hebei Jianzhi Casting Group Ltd Pangzhuangzi Yutian County Tangshan064100 China College Tangshan University Key Lab of Intelligent Data Information Processing and Control of Hebei Province Key Lab of Intelligent Motion Control System of Tangshan City Intelligence and Information Engineering Tangshan063000 China North China University of Science and Technology College of Electrical Engineering Tangshan063210 China Kernel University FullertonCA92832 United States

ISBN: (纸本)9789887581581

This paper discusses the H∞ consensus problem of leader-follower multi-agent systems. The controller for each agent is crafted to utilize comprehensive information from all connected agents, while an innovative event-triggered strategy is incorporated to minimize communication costs. Based on the Lyapunov function theory, an H∞ controller is proposed that can ensure both system stability and a prescribed disturbance attenuation level γ. Finally, a numerical example validated the effectiveness of the proposed method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Fractional-Order Sliding Mode Finite Time Control for the Speed and Tension System of the Reversible Cold Strip Rolling Mill

Fractional-Order Sliding Mode Finite Time Control for the Sp...

引用

第43届中国控制会议

作者： Zhipeng Lin Le Liu Ranyang Deng Yiming Fang Miao Xu Key Laboratory of Intelligent Rehabilitation and Neromodulation of Hebei Province Yanshan University Key Lab of Intelligent Data Information Processing and Control of Hebei Province Tangshan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

To enhance the tracking control performance of the speed and tension system of the reversible cold strip rolling mill and reduce the impact of uncertainties,a fractional-order sliding mode finite time control strategy is proposed based on adaptive sliding mode disturbance ***,novel fractional-order adaptive sliding mode disturbance observers(NFOASMDOs)are employed to dynamically observe the unmatched uncertainties in the system,thereby effectively enhancing the tracking control ***,the dynamic surface backstepping control is combined with the fractional-order sliding mode control to complete the designs of the finite time fractional-order sliding mode controllers(FTFOSMCs),which suppress the system's chattering phenomenon effectively,and avoid the "differential explosion" ***,the feasibility of the presented control method is illustrated by the simulation comparison study.

关键词： Reversible cold strip rolling mill Adaptive sliding mode disturbance observer Fractional-order sliding mode control Dynamic surface backstepping control

来源：评论

学校读者我要写书评

暂无评论

LCV2I: Communication-Efficient and High-Performance Collaborative Perception Framework with Low-Resolution LiDAR

arXiv

引用

arXiv 2025年

作者： Feng, Xinxin Sun, Haoran Zheng, HaiFeng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou35108 China

Vehicle-to-Infrastructure (V2I) collaborative perception leverages data collected by infrastructure’s sensors to enhance vehicle perceptual capabilities. LiDAR, as a commonly used sensor in cooperative perception, is widely equipped in intelligent vehicles and infrastructure. However, its superior performance comes with a correspondingly high cost. To achieve low-cost V2I, reducing the cost of LiDAR is crucial. Therefore, we study adopting low-resolution LiDAR on the vehicle to minimize cost as much as possible. However, simply reducing the resolution of vehicle’s LiDAR results in sparse point clouds, making distant small objects even more blurred. Additionally, traditional communication methods have relatively low bandwidth utilization efficiency. These factors pose challenges for us. To balance cost and perceptual accuracy, we propose a new collaborative perception framework, namely LCV2I. LCV2I uses data collected from cameras and low-resolution LiDAR as input. It also employs feature offset correction modules and regional feature enhancement algorithms to improve feature representation. Finally, we use regional difference map and regional score map to assess the value of collaboration content, thereby improving communication bandwidth efficiency. In summary, our approach achieves high perceptual performance while substantially reducing the demand for high-resolution sensors on the vehicle. To evaluate this algorithm, we conduct 3D object detection in the real-world scenario of DAIR-V2X, demonstrating that the performance of LCV2I consistently surpasses currently existing algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Heterophilic Graph Representation Learning Based on Multi-Order information Extraction and High and Low Pass Filters 10

Heterophilic Graph Representation Learning Based on Multi-Or...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Li, Xinyu Yang, Yingjie Guo, Kun Zhang, Qishan Fuzhou University College of Computer and Data Science Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China De Montfort University School of Computer Science and Informatics Leicester United Kingdom Shanghai International Studies University College of Economics and Humanities Shanghai China

ISBN: (纸本)9798331520861

Real-world networks can be divided into homophilic and heterophilic graphs. Significantly, many nodes tend to be heterophilic in a homophilic graph. Graph representation learning in heterophilic graphs has attracted considerable significance in recent years as it breaks the homophily assumption and achieves higher-quality graph embeddings. However, existing heterophilic graph representation learning methods often mix attribute and topological information, neglecting the mutual exclusion between attribute information and topological information. Furthermore, algorithms in heterogeneous graphs usually rely on specific matrix structures to capture high-order information, which may restrict the applicability of these methods. To tackle these issues, this paper proposes a GNN-based strategy for Heterophilic graph Representation Learning based on Multi-order information extraction and High and Low pass filters (HRLMHL). First, we designed two relatively independent modules to learn attribute information and topological information, respectively, to address the issue of mismatch. Second, we built a multi-order information extraction module to extract multi-order similarity features, thereby achieving the learning of high-order graph information. Experiments on real datasets show that the node classification accuracy is superior to that of the state-of-the-art methods on most datasets. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion Considering Anomalies

BTD-GTAN: Federated Traffic Flow Prediction with Multimodal ...

引用

International Conference on Computers, Communications, and Systems (ICCCS)

作者： Shaofei Feng Xinxin Feng Lixia Xu Haifeng Zheng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou China

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

Predicting traffic flow effectively alleviates congestion. However, traditional methods tend to rely solely on historical traffic flow data, overlooking the correlation between multimodal traffic data, such as speed and occupancy collected by sensors placed on the road. This limitation results in low tolerance for abnormal situations. Moreover, the decentralization of multimodal data on edge devices may pose data anomalies or partial modal missing due to equipment damage or absence. To address these challenges, we propose a Block-Term tensor decomposition-based multimodal data feature fusion algorithm for traffic prediction. This approach enhances the accuracy and robustness of traffic flow prediction by considering correlations between various modal data, such as speed and occupancy rate. In response to the issues of scattered multimodal data anomalies and missing data on edge devices, and to ensure address privacy and security issues, we employ federated learning methods to achieve adaptive extraction and fusion of multi-modal data at the edges. Our method is tested on a real highway dataset, demonstrating superior prediction performance and robustness compared to traditional methods, particularly in the context of data anomalies or missing modalities.

关键词： Performance evaluation Data privacy Accuracy Tensors Correlation Federated learning Distributed databases

来源：评论

学校读者我要写书评

暂无评论

Off-Grid Parameter Estimation for OFDM-Based ISAC Systems with Incomplete Data

Off-Grid Parameter Estimation for OFDM-Based ISAC Systems wi...

引用

IEEE Conference on Wireless Communications and networking

作者： Muyao Ling Xinxin Feng Haifeng Zheng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

In the 6G environment, addressing the challenges of data loss and off-grid issues during target parameter estimation poses a significant challenge for the Integrated Sensing and Communication (ISAC) system. In the ISAC framework, a commonly used method for parameter estimation is compressive sensing. However, compressive sensing may encounter off-grid issues in continuous parameter estimation. In contrast, the atomic norm proves effective in addressing off-grid problems, making it more suitable for continuous parameter estimation. We explore the application of the atomic norm in ISAC and further derive an ISAC model based on OFDM (Orthogonal Frequency Division Multiplexing) utilizing the atomic norm under conditions of incomplete data. To ensure improved convergence speed and accuracy of our algorithm, we employ the Alternating Direction Method of Multipliers (ADMM) for iterative implementation. Experimental results demonstrate that our proposed AN algorithm accurately estimates target parameters in the presence of data loss, exhibiting higher precision and robustness compared to traditional methods.

关键词： Parameter estimation Accuracy OFDM Noise reduction Estimation Robustness Iterative algorithms

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：