检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shool of Information Technology Carleton University Canada

ISBN: (纸本)9798891761964

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: https://***/howard-hou/VisualRWKV. © 2025 Association for Computational Linguistics.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient-Learning Grasping and Pushing in Dense Stacking via Mask Function and Pixel Overlap Rate 7

Efficient-Learning Grasping and Pushing in Dense Stacking vi...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Lian, Jie Jiang, Juncheng Qiu, Chaochao Pan, Qinghui Dong, Yongxiang Wang, Zhao Wang, Dong Dalian University of Technology School of Control Science and Engineering Dalian China University of Science and Technology Liaoning Shool of Computer Science and Software Engineering China

ISBN: (纸本)9798350363173

In the field of robotic grasping, grasping tightly stacked objects is a formidable challenge. The presence of non-target objects significantly increases the risk of grasping failure. To solve this problem, the aim is to take action while grasping, reduce clutter, and effectively complete grasping tasks. Based on deep reinforcement learning, the Efficient Learning Grasping(ELG) framework is proposed that integrates pushing actions alongside grasping to efficiently pick up objects from cluttered environments with reduced training time. However, in the process of grasping, the agent is rewarded only when the grasp is successful, so the data collection is extremely inefficient and spends a lot of time on the training of grasping strategy. In our work, two strategies are proposed to improve the training efficiency. First, two mask functions are introduced as prior knowledge to enable the agent to focus on more meaningful regions while ignoring some unnecessary regions, aiming at effective learning. Second, The Pixel Overlap Rate (POR) is introduced to quantify the environment clutter level, and set a new push action reward function based on the POR. The implementation of the above ideas in a simulation environment and transferred the learned models to the real world and verified them in practice. Compared with existing method, our method improves the training efficiency of the initial algorithm while having a higher success rate of grasping. Detailed grasping video at https://***/CqtSvaVl60M. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Thinking on Design and Realization of Source Code Online Evaluation System

Thinking on Design and Realization of Source Code Online Eva...

引用

2013 2nd International Conference on Social science and Education(ICSSE 2013)

作者： Yuansong Li Software Engineering Department Shool of Computer Science Sichuan University of Science and Engineering

The traditional evaluation procedure is mainly manual evaluation in practical teaching field. Such work is very complicated. With the constant development and improvement of computer technology, there are high requirements for the programming level of workers and such traditional evaluation method has a series of problems. To better impel students to learn programming and effectively ease the burden of teachers, this paper designs a source code online evaluation system which can effectively improve the evaluation level.

关键词： Source code, Evaluation, System, Design

来源：评论

学校读者我要写书评

暂无评论

PoW and PoS and Related Applications

PoW and PoS and Related Applications

引用

2021 International Conference on Electronic Information engineering and computer science, EIECS 2021

作者： Ouyang, Zhiqiang Shao, Jie Zeng, Yifeng School of Computer Science and Engineering Sun Yat-sen University Guangzhou China University of Washington Department of Mathematics WA United States Shool of Software Dalian University of Technology Dalian China

ISBN: (纸本)9781665416740

Consensus protocols can help guarantee security and sustainability to maintain the decentralized Blockchain system used in different scenarios and applications due to their different features. There are two main prevalent protocols, Proof of Work (PoW) used in Bitcoin and Proof of Stake (PoS) used in Ethereum. This paper reviews these two consensus protocols, PoW and PoS, and their related improvements and applications. We first introduce the basic concepts, implementations, advantages, and disadvantages of PoW and PoW and make a detailed comparison between these two protocols. We find that though providing security when honest participants are the majority, PoW may lead to excessive power consumption. While PoS is relatively insecure and leads to monopoly (centralization), though energy efficient by discarding complex hash operations. Therefore, some newly proposed consensus protocols have attempted to find a pleasant compromise between these two classic protocols. After a detailed analysis, we investigate the researches related to the defect improvements of PoS and PoW. Finally, we describe various applications of PoS and PoW, including cryptocurrencies and information storage. © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Efficient-Learning Grasping and Pushing in Dense Stacking via Mask Function and Pixel Overlap Rate

Efficient-Learning Grasping and Pushing in Dense Stacking vi...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Jie Lian Juncheng Jiang Chaochao Qiu Qinghui Pan Yongxiang Dong Zhao Wang Dong Wang School of Control Science and Engineering Dalian University of Technology Dalian China Shool of Computer Science and Software Engineering University of Science and Technology Liaoning

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

关键词： Training Stacking Grasping Production Data collection Deep reinforcement learning Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

A modeling approach of mobile ad hoc networks survivability model

A modeling approach of mobile ad hoc networks survivability ...

引用

1st International Conference on Information science and engineering, ICISE2009

作者： Wang, Haiquan Ma, Xinyi Xia, Chunhe Hao, Senshen State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing China Key Laboratory of Beijing Network Technology Beihang University Beijing China College of Software Beihang University Beijing China Shool of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9780769538877

Survivability has become a focal point of research. Simulation is a common method for experimental verification to identify the advantages and deficiencies of survivability models and architectures. This paper proposes a modeling approach of mobile ad hoc network survivability model which support the automatic transformation to a simulation instance. A new survivability model MARC based on the idea of ARC model is conducted. Within this model, the concepts of network services and events are analyzed and formally descript in details. Base on these works, we design MARCDL and outline the important EBNF in this paper. Use of this language is illustrated by a case study. ©2009 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

arXiv

引用

arXiv 2024年

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrative computing method for the prediction of zinc-binding sites in proteins

Integrative computing method for the prediction of zinc-bind...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hui Li Dechang Pi Yinghong Liang Chuanming Chen Yongzhi Liu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Shool of Software Engineering Jinling Institute of Technology Nanjing Jiangsu China

ISBN: (纸本)9781509061839

A large number of metalloproteins contained in Protein Data Bank, taking metal ions as cofactors, have important biological functions. As the second most abundant bound trace metal elements in organism, zinc ion plays an important regulatory role in the biological growth and development, disease control, DNA synthesis. So, research on the area of zinc-binding protein sites has an important significance. Because of the availability of protein sequence information, a series of predictive tools based on sequence for zinc-binding sites in proteins have been developed. But presently, there is little research on the integration of these tools. Based on this, an integrative predictor termed meta-zincPrediction is presented in the paper to combine the predictive tools. The linear regression method is used in the integrated approach to combine the scores of different prediction tools, the parameters are adjusted and optimized until to the optimal. Tested on the non-redundant Zhao_dataset, AURPC value of meta-zincPrediction reached nearly 0.9, an increase of 2% -9% than other three predictors, and other performance indexes were also improved mostly. Moreover, the prediction ability of meta-zincPrediction was better than other three predictors, regardless of zinc-binding sites for all four types of residues, or zinc-binding sites for a single type of residues. Our method can not only be applied to large-scale identification of zinc-binding sites based on sequence information, but also be useful for the inference of protein function.

关键词： Proteins Tools Ions Metals Linear regression Machine learning algorithms Predictive models

来源：评论

学校读者我要写书评

暂无评论

From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation

From Handcrafted Features to LLMs: A Brief Survey for Machin...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Haofei Zhao Yilun Liu Shimin Tao Weibin Meng Yimeng Chen Xiang Geng Chang Su Min Zhang Hao Yang Shool of Computer Science and Engineering Northeastern University Shenyang China Huawei China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT. After two decades of evolution, QE has yielded a wealth of results. This article provides a comprehensive overview of QE datasets, annotation methods, shared tasks, methodologies, challenges, and future research directions. It begins with an introduction to the background and significance of QE, followed by an explanation of the concepts and evaluation metrics for word-level QE, sentence-level QE, document-level QE, and explainable QE. The paper categorizes the methods developed throughout the history of QE into those based on handcrafted features, deep learning, and Large Language Models (LLMs), with a further division of deep learning-based methods into classic deep learning and those incorporating pre-trained language models (LMs). Additionally, the article details the advantages and limitations of each method and offers a straightforward comparison of different approaches. Finally, the paper discusses the current challenges in QE research and provides an outlook on future research directions.

关键词： Deep learning Learning systems Surveys Measurement Annotations Neural networks Estimation

来源：评论

学校读者我要写书评

暂无评论

SHREC 2019 - Monocular image based 3D model retrieval 12

SHREC 2019 - Monocular image based 3D model retrieval

引用

12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for computer Graphics, EG 2019

作者： Li, Wenhui Liu, Anan Nie, Weizhi Song, Dan Li, Yuqian Wang, Weijie Xiang, Shu Zhou, Heyu Bui, Ngoc-Minh Cen, Yunchi Chen, Zenian Chung-Nguyen, Huy-Hoang Diep, Gia-Han Do, Trong-Le Doubrovski, Eugeni L. Duong, Anh-Duc Geraedts, Jo M.P. Guo, Haobin Hoang, Trung-Hieu Li, Yichen Liu, Xing Liu, Zishun Luu, Duc-Tuan Ma, Yunsheng Nguyen, Vinh-Tiep Nie, Jie Ren, Tongwei Tran, Mai-Khiem Tran-Nguyen, Son-Thanh Tran, Minh-Triet Vu-Le, The-Anh Wang, Charlie C.L. Wang, Shijie Wu, Gangshan Yang, Caifei Yuan, Meng Zhai, Hao Zhang, Ao Zhang, Fan Zhao, Sicheng Shool of Electrical and Information Engineering Tianjin University China University of Science VNU-HCM Viet Nam State Key Laboratory of Virtual Reality Technology and System Beihang University China Delft University of Technology Netherlands University of Information Technology VNU-HCM Viet Nam Nanjing University China SuoAo Technology Center SAEE University of Science and Technology Beijing China Chinese University of Hong Kong Hong Kong School of Software Dalian University of Technology China Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Ocean University of China China

ISBN: (纸本)9783038680772

Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this promising research, we organize this SHREC track and build the first monocular image based 3D object retrieval benchmark by collecting 2D images from ImageNet and 3D objects from popular 3D datasets such as NTU, PSB, ModelNet40 and ShapeNet. The benchmark contains classified 21,000 2D images and 7,690 3D objects of 21 categories. This track attracted 9 groups from 4 countries and the submission of 20 runs. To have a comprehensive comparison, 7 commonly-used retrieval performance metrics have been used to evaluate their retrieval performance. The evaluation results show that the supervised cross domain learning get the superior retrieval performance (Best NN is 97.4 %) by bridging the domain gap with label information. However, there is still a big challenge for unsupervised cross domain learning (Best NN is 61.2%), which is more practical for the real application. Although we provided both view images and OBJ file for each 3D model, all the participants use the view images to represent the 3D model. One of the interesting work in the future is directly using the 3D information and 2D RGB information to solve the task of monocular Image based 3D model retrieval. © 2019 The Author(s)

关键词： 3D modeling

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：