检索结果-内蒙古大学图书馆

2020 International Conference on Electronics, Communications and Information technology, CECIT 2020

作者： Shang, Mengjun Yin, Longxiang Xu, Ning School of Information Engineering Wuhan University of Technology Wuhan China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

Nowadays, memristor-based neural network accelerators have been widely studied due to their outstanding performance in massive parallel vector matrix multiplication. However, the memristor is sensitive to temperature and its on/off state operation window can be seriously degraded by the increasing temperature, which may lead to computation failures in memristor -based NN accelerators. In this work, we establish an electro-thermal simulation platform to evaluate the temperature impact on memristor -based NN accelerators. With this platform, we first investigate the impact on computation accuracy with the temperature increase in different NN layers in the accelerators. We then apply a temperature-aware NN weight mapping scheme to the most temperature-sensitive layer and achieve 28.89% improvement in computation accuracy, which only has 0.06% difference with the improvement achieved by applied the mapping scheme to the whole NN model. This finding can help to simplify the temperature-aware hardware optimization design in memristor-based neural network accelerators and reduce the power consumption. © Published under licence by IOP Publishing Ltd.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

FIRE: a dataset for feedback integration and refinement evaluation of multimodal models 24

FIRE: a dataset for feedback integration and refinement eval...

引用

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

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DU-DARTS: Decreasing the Uncertainty of Differentiable architecture Search 32

DU-DARTS: Decreasing the Uncertainty of Differentiable Archi...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Lu, Shun Hu, Yu Yang, Longxing Sun, Zihao Mei, Jilin Zeng, Yiming Li, Xiaowei Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Tecent ADlab China

Differentiable Neural architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for selecting the truly important operation, thus leading to serious performance collapse. In this work, we decrease the uncertainty of differentiable architecture search (DU-DARTS) by enforcing the distribution of architecture parameters to approach the one-hot categorical distribution and by replacing the zero operation with a gate switch. Without any extra search cost, our method achieves state-of-the-art performance with 2.32%, 16.74%, and 24.1% test error on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Moreover, DU-DARTS can robustly find an excellent architecture on NAS-Bench-1Shot1 and NAS-Bench-201, which further demonstrates the effectiveness of our method. The source code is available at https://***/ShunLu91/DU-DARTS. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy 38

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guan, Zhenyu Kong, Xiangyu Zhong, Fangwei Wang, Yizhou Institute for Artificial Intelligence Peking University China College of Computer Science Beijing Information Science and Technology University China School of Artificial Intelligence Beijing Normal University China Center on Frontiers of Computing Studies School of Computer Science Nat'l Eng Research Center of Visual Technology Peking University China State Key Laboratory of General Artificial Intelligence BIGAI China

Diplomacy is one of the most sophisticated activities in human society, involving complex interactions among multiple parties that require skills in social reasoning, negotiation, and long-term strategic planning. Previous AI agents have demonstrated their ability to handle multi-step games and large action spaces in multi-agent tasks. However, diplomacy involves a staggering magnitude of decision spaces, especially considering the negotiation stage required. While recent agents based on large language models (LLMs) have shown potential in various applications, they still struggle with extended planning periods in complex multi-agent settings. Leveraging recent technologies for LLM-based agents, we aim to explore AI's potential to create a human-like agent capable of executing comprehensive multi-agent missions by integrating three fundamental capabilities: 1) strategic planning with memory and reflection;2) goal-oriented negotiation with social reasoning;and 3) augmenting memory through self-play games for self-evolution without human in the loop. Project page: https://***/view/richelieu-diplomacy. © 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

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

ISAR imaging of complex moving targets based on coherent accumulation type non-uniform sampling third-order autocorrelation function

ISAR imaging of complex moving targets based on coherent acc...

引用

International Conference on computer Engineering and Applications (ICCEA)

作者： Zongyang Sun Tong Zhang Kangfa Xu Qiheng Song Aviation Key Laboratory of Science and Technology on Airborne and Missle-Borne Computer Xi’an Aeronautics Computing Technique Research Institute AVIC School of Computer Science Northwestern Polytechnical University Xi’an China Aviation Key Laboratory of Science and Technology on Airborne and Missle-Borne Computer Xi’an Aeronautics Computing Technique Research Institute AVIC Xi’an China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

ISAR imaging algorithm based on Coherent accumulation type non-uniform sampling third-order autocorrelation function (CANS-TAF) is proposed for complex moving targets. CANS-TAF defines a new non-uniform sampling third-order autocorrelation function (NTAF), which enables signal energy to accumulate coherently in the slow time delay two-dimensional data domain and improves the noise resistance performance of CPS parameter estimation. And the implementation process of this algorithm only requires complex multiplication, Scaled Fourier Transform (SFT) and Complete the Fast Fourier Transform (FFT) operation. It is a new non search parameter estimation algorithm that does not require tedious parameter search processes or the use of non-uniform Fourier transform. The final simulation experimental results demonstrate the superiority of the proposed algorithm in terms of Noise immunity.

关键词： Resistance Parameter estimation Fast Fourier transforms Signal processing algorithms Imaging Resists Radar

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution

arXiv

引用

arXiv 2025年

作者： Zhu, Jizhao Shi, Akang Li, Zixuan Bai, Long Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science Shenyang Aerospace University Shenyang China

In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution. Existing robust benchmark datasets have two key limitations: 1) They generate only a limited range of perturbations for a single Information Extraction (IE) task, which fails to evaluate the robustness of UIE models effectively;2) They rely on small models or handcrafted rules to generate perturbations, often resulting in unnatural adversarial examples. Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench, which utilizes LLMs to generate more diverse and realistic perturbations across different IE tasks. Based on this dataset, we comprehensively evaluate existing UIE models and reveal that both LLM-based models and other models suffer from significant performance drops. To improve robustness and reduce training costs, we propose a data-augmentation solution that dynamically selects hard samples for iterative training based on the model’s inference loss. Experimental results show that training with only 15% of the data leads to an average 7.5% relative performance improvement across three IE tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Design and development of intelligent well logging interpretation system 41

Design and development of intelligent well logging interpret...

引用

第41届中国控制会议

作者： Saifei Ma Jin Tang Zerui Li Kun Li Wenjun Lv School of Computer Science and Technology Anhui University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Key Laboratory of Multimodal Cognitive Computing Anhui University Institute of Advanced Technology University of Science and Technology of China Department of Automation University of Science and Technology of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,the traditional well logging interpretation method manually operated by experts has shown some problems,such as low efficiency and poor results,facing the challenges of high dimension,diversity and complexity of current logging *** the progress of artificial intelligence,its effectiveness and efficiency in logging interpretation have gradually attracted researchers' ***,the uncertainty of logging process necessitates the preprocess of collected logging data before employing the artificial intelligence ***,an intelligent well logging interpretation system is designed and developed in this *** the logging data anomalies may include data repetition,null value,etc.,a specific preprocessing module is designed in the system to tackle the data anomalies,so as to ensure that the data input into the algorithms is correct and *** governance can effectively enhance the effectiveness of data,so it is used to guide the design and implementation of logging interpretation ***,user mode and debug mode are designed to solve the problem of cross functional conflict in data governance.

关键词： System Development Logging Interpretation Data Governance Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

The Adaptive Fault-tolerant Routing Based on an Improved Local Security Information Model of the Exchanged Hypercube 21

The Adaptive Fault-tolerant Routing Based on an Improved Loc...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud computing, 16th IEEE International Conference on Social computing and Networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Yazhi Luo, Chuanwen Wang, Guijuan Zhang, Li Lv, Mengjie Yu, Jiguo Qilu University of Technology School of Computer Science and Technology Jinan China Beijing Forestry University School of Information Science and Technology Beijing China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Nanjing University of Posts and Telecommunications College of Computer Nanjing China Qilu University of Technology Shandong Academy of Sciences Big Data Research Institute Jinan China

ISBN: (纸本)9798350329223

With the increasing amount of computation in high-performance computing, the scale of interconnection networks is becoming larger and larger. It is inevitable that processors or links in the network become faulty. Therefore, it is very important for a processor to understand the security status of itself and neighbors, and then adaptively and reliably communicate. However, the existing security information models consider faulty processors or faulty links separately, and do not consider the situation where both processors and links fail simultaneously. The Exchanged Hypercube is an excellent interconnection network structure which achieves a balance between network functionality and hardware overhead while preserving many excellent properties of the Hypercube. In this paper, we propose an adaptive fault-tolerant routing algorithm of the Exchanged Hypercube based on an improved local security information model, which considers the faulty processors and faulty links simultaneously. This algorithm always can select suitable processors for routing based on the local security information and unsafe coefficients of processors, which greatly reduces the impact of the faulty of networks. The adaptive fault-tolerant routing algorithm of the Exchanged Hypercube network is not only suitable for regular networks but also for heterogeneous networks since the Exchanged Hypercube is a semi regular network. Sufficient experimental results show that the algorithm proposed in this paper has a lower packet loss rate, a higher success rate, and a shorter average path length. © 2023 IEEE.

关键词： Hypercube networks

来源：评论

学校读者我要写书评

暂无评论

Modelization and analysis of dynamic heterogeneous redundant system

Modelization and analysis of dynamic heterogeneous redundant...

引用

作者： Wang, Wei Li, Guangsong Gai, Keke Tang, Yazhe Yang, Benchao Si, Xueming State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou China School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China Shanghai Key Laboratory of Data Science Fudan University Shanghai China

With the development and popularization of Internet technology, network security has become the focus of attention. Vulnerabilities and back doors are regarded as two of the main reasons of network security problems. Dynamic heterogeneous redundant (DHR) architecture is a typical framework of cyberspace mimic defense. It can make use of untrusted hardware and software components to construct a high reliable and high security information system. In this article, a mathematical model is set up for the DHR architecture, and the system security is characterized by vulnerability consistency rate and success rate of system attack. The antiattack ability of the DHR system is analyzed using the mathematical model. © 2020 John Wiley & Sons, Ltd.

关键词： Network security

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：