检索结果-内蒙古大学图书馆

VIS+AI: integrating visualization with artificial intelligence for efficient data analysis

学校读者我要写书评

暂无评论

Frontiers of computer science 2023年第6期17卷 13-24页

作者： Xumeng WANG Ziliang WU Wenqi HUANG Yating WEI Zhaosong HUANG Mingliang XU Wei CHEN College of Computer Science Nankai UniversityTianjin 300381China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China Digital Grid Research Institute China Southern Power GridGuangzhou 510670China Huawei Technologies Co. Ltd.Hangzhou 310052China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou 450001China Engineering Research Center of Ministry of Education on Intelligent Swarm Systems Zhengzhou UniversityZhengzhou 450001China National Supercomputing Center in Zhengzhou Zhengzhou 450001China Laboratory of Art and Archaeology Image Zhejiang UniversityHangzhou 310058China

Visualization and artificial intelligence(AI)are well-applied approaches to data *** one hand,visualization can facilitate humans in data understanding through intuitive visual representation and interactive *** the other hand,AI is able to learn from data and implement bulky tasks for *** complex data analysis scenarios,like epidemic traceability and city planning,humans need to understand large-scale data and make decisions,which requires complementing the strengths of both visualization and *** studies have introduced AI-assisted visualization as AI4VIS and visualization-assisted AI as ***,how can AI and visualization complement each other and be integrated into data analysis processes are still *** this paper,we define three integration levels of visualization and *** highest integration level is described as the framework of VIS+AI,which allows AI to learn human intelligence from interactions and communicate with humans through visual *** also summarize future directions of VIS+AI to inspire related studies.

关键词： visualization artificial intelligence data analysis knowledge generation

Datalab: A Unified Platform for LLM-Powered Business Intelligence

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Weng, Luoxuan Tang, Yinghao Feng, Yingchaojie Chang, Zhuo Chen, Peng Chen, Ruiqin Feng, Haozhe Hou, Chen Huang, Danqing Li, Yang Rao, Huaming Wang, Haonan Wei, Canshi Yang, Xiaofeng Zhang, Yuhui Zheng, Yifeng Huang, Xiuqi Zhu, Minfeng Ma, Yuxin Cui, Bin Chen, Wei State Key Lab of CAD&CG Zhejiang University China Tencent Inc. China Zhejiang University China Southern University of Science and Technology China School of Computer Science Peking University China

Business intelligence (BI) transforms large volumes of data within modern organizations into actionable insights for informed decision-making. Recently, large language model (LLM)-based agents have streamlined the BI workflow by automatically performing task planning, reasoning, and actions in executable environments based on natural language (NL) queries. However, existing approaches primarily focus on individual BI tasks such as NL2SQL and NL2VIS. The fragmentation of tasks across different data roles and tools lead to inefficiencies and potential errors due to the iterative and collaborative nature of BI. In this paper, we introduce Datalab, a unified BI platform that integrates a one-stop LLM-based agent framework with an augmented computational notebook interface. Datalab supports a wide range of BI tasks for different data roles by seamlessly combining LLM assistance with user customization within a single environment. To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks. Extensive experiments demonstrate that Datalab achieves state-of-the-art performance on various BI tasks across popular research benchmarks. Moreover, Datalab maintains high effectiveness and efficiency on real-world datasets from Tencent, achieving up to a 58.58% increase in accuracy and a 61.65% reduction in token cost on enterprise-specific BI tasks. © 2024, CC BY.

关键词： Efficiency

Wind resistance aerial path planning for efficient reconstruction of offshore ship

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2022年第1期15卷 1881-1904页

作者： Tao Liu Ruiqi Shen Zhengling Lei Yuchi Huo Jiansen Zhao Xiaogang Xu College of Transport & Communications Shanghai Maritime UniversityShanghaiPeople’s Republic of China Merchant Marine College Shanghai Maritime UniversityShanghaiPeople’s Republic of China College of Engineering Science and Technology Shanghai Ocean UniversityShanghaiPeople’s Republic of China State Key Lab of CAD&CG Zhejiang UniversityHangzhouPeople’s Republic of China Intelligent Transportation Research Center Zhejiang LabHangzhouPeople’s Republic of China School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhouPeople’s Republic of China

When the unmanned aerial vehicle(UAV)is applied to three-dimensional(3D)reconstruction of the offshore ship,it faces two problems:the battery capacity limitation of the UAV and the disturbance of the wind in the *** disturbance is generally not considered in the path planning process of the existing UAV 3D reconstruction path planning ***,the planned path is only suitable for no-wind or light-wind *** the 3D reconstruction of ship targets,we propose a UAV path planning method that can satisfy both reconstruction efficiency and wind disturbance resistance ***,the concept of model surface complexity is proposed to generate a more efficient candidate view ***,the Min–Max strategy and a new viewpoint construction method are used to generate the initial ***,combined with the wind field model,a method for generating a stable path against wind disturbance based on the idea of interval optimization is *** results demonstrate that our method can adaptively determine the number of sample points and viewpoints according to ship’s geometric characteristics and further reduce the number of viewpoints without significantly affecting the reconstruction quality;the path planned by our method is also stable against wind disturbance.

关键词： Multi-view 3D reconstruction aerial path planning wind resistance UAV

TPGP: Temporal-Parametric Optimization with Deep Grasp Prior for Dexterous Motion Planning

学校读者我要写书评

暂无评论

TPGP: Temporal-Parametric Optimization with Deep Grasp Prior...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Haoming Li Qi Ye Yuchi Huo Qingtao Liu Shijian Jiang Tao Zhou Xiang Li Yang Zhou Jiming Chen College of Control Science and Engineering Zhejiang University Hangzhou China The College of Control Science and Engineering the State Key Laboratory of Industrial Control Technology Zhejiang University The Key Key Lab of CS&AUS of Zhejiang Province State Key Lab of CAD&CG Zhejiang University Zhejiang Lab OPPO US Research Center

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Grasping motion planning aims to find a feasible grasping trajectory in the configuration space given an input target grasp. While optimizing grasp motion with two or three-fingered grippers has been well studied, the study on natural grasp motion planning with a dexterous hand remains a very challenging problem due to the high dimensional working space. In this work, we propose a novel temporal-parametric grasp prior (TPGP) optimization method to simplify the difficulty of grasping trajectory optimization for the dexterous hand while maintaining smooth and natural properties of the grasping motion. Specifically, we formulate the discrete trajectory parameters into a temporal-based parameterization, where the prior constraint provided by a hand poser network, is introduced to ensure that hand pose is natural and reasonable throughout the trajectory. Finally, we present a joint target optimization strategy to enhance the target pose for more feasible trajectories. Extensive validations on two public datasets show that our method outperforms state-of-the-art methods regarding grasp motion on various metrics.

关键词： Measurement Employment Optimization methods Grasping Planning Robotics and automation Grippers

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Zhengkai Fu, Zhihang Liu, Kai Xie, Liang Lin, Binbin Wang, Wenxiao Cai, Deng Wu, Yue Ye, Jieping State Key Lab of CAD&CG Zhejiang University China Alibaba Cloud College of Biomedical Engineering & Instrument Science Zhejiang University China College of Computer Science and Technology Zhejiang University of Technology China School of Software Technology Zhejiang University China Fullong Inc China

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when models, having been trained on the fact "A is B", struggle to generalize this knowledge to infer that "B is A". In this paper, we examine the manifestation of the reversal curse across various tasks and delve into both the generalization abilities and the problem-solving mechanisms of LLMs. This investigation leads to a series of significant insights: (1) LLMs are able to generalize to "B is A" when both A and B are presented in the context as in the case of a multiple-choice question. (2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents. For example, this generalization only applies to biographies structured in "[Name] is [Description]" but not to "[Description] is [Name]". (3) We propose and verify the hypothesis that LLMs possess an inherent bias in fact recalling during knowledge application, which explains and underscores the importance of the document structure to successful learning. (4) The negative impact of this bias on the downstream performance of LLMs can hardly be mitigated through training alone. These findings offer a novel perspective on interpreting LLMs' generalization through their intrinsic mechanisms and provide insights for developing more effective learning methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Data description

AutoManual: constructing instruction manuals by LLM agents via interactive environmental learning 24

学校读者我要写书评

暂无评论

AutoManual: constructing instruction manuals by LLM agents v...

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

作者： Minghao Chen Yihang Li Yanting Yang Shiyu Yu Binbin Lin Xiaofei He School of Computer Science Hangzhou Dianzi University State Key Lab of CAD&CG Zhejiang University School of Software Technology Zhejiang University NingBo Port Group School of Software Technology Zhejiang University and Fullong Inc.

ISBN: (纸本)9798331314385

Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agents typically require elaborate design and expert prompts to solve tasks in specific domains, which limits their adaptability. We introduce AutoManual, a framework enabling LLM agents to autonomously build their understanding through interaction and adapt to new environments. AutoManual categorizes environmental knowledge into diverse rules and optimizes them in an online fashion by two agents: 1) The Planner codes actionable plans based on current rules for interacting with the environment. 2) The Builder updates the rules through a well-structured rule system that facilitates online rule management and essential detail retention. To mitigate hallucinations in managing rules, we introduce a case-conditioned prompting strategy for the Builder. Finally, the Formulator agent compiles these rules into a comprehensive manual. The self-generated manual can not only improve the adaptability but also guide the planning of smaller LLMs while being human-readable. Given only one simple demonstration, AutoManual significantly improves task success rates, achieving 97.4% with GPT-4-turbo and 86.2% with GPT-3.5-turbo on ALFWorld benchmark tasks. The code is available at https://***/minghchen/automanual.

关键词：

NFTVis: Visual Analysis of NFT Performance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yan, Fan Wang, Xumeng Mao, Ketian Zhang, Wei Chen, Wei State Key Lab of CAD&CG Zhejiang University China College of Computer Science Nankai University China Laboratory of Art and Archaeology Image Zhejiang University Ministry of Education China

A non-fungible token (NFT) is a data unit stored on the blockchain. Nowadays, more and more investors and collectors (NFT traders), who participate in transactions of NFTs, have an urgent need to assess the performance of NFTs. However, there are two challenges for NFT traders when analyzing the performance of NFT. First, the current rarity models have flaws and are sometimes not convincing. In addition, NFT performance is dependent on multiple factors, such as images (high-dimensional data), history transactions (network), and market evolution (time series). It is difficult to take comprehensive consideration and analyze NFT performance efficiently. To address these challenges, we propose NFTVis, a visual analysis system that facilitates assessing individual NFT performance. A new NFT rarity model is proposed to quantify NFTs with images. Four well-coordinated views are designed to represent the various factors affecting the performance of the NFT. Finally, we evaluate the usefulness and effectiveness of our system using two case studies and user studies. Copyright © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

WaveLines:towards effective visualization and analysis of stability in power grid simulation

学校读者我要写书评

暂无评论

Frontiers of computer science 2021年第6期15卷 19-30页

作者： Tianye ZHANG Qi WANG Liwen LIN Jiazhi XIA Xiwang XU Yanhao HUANG Xiaonan LUO Wenting ZHENG Wei CHEN The state key lab of CAD&CG Zhejiang UniversityHangzhou 310058China School of Computer Science and Engineering Central South UniversityChangsha 410083China The State Key Lab of Power Grid Safety and Energy Conservation China Electric Power Research InstituteBeijing 100192China School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin 541004China

Closely related to the safety and stability of power grids,stability analysis has long been a core topic in the electric *** approaches employ computational simulation to make the quantitative judgement of the grid stability under distinctive *** lack of in-depth data analysis tools has led to the difficulty in analytical tasks such as situation-aware analysis,instability reasoning and pattern *** facilitate visual exploration and reasoning on the simulation data,we introduce WaveLines,a visual analysis approach which supports the supervisory control of multivariate simulation time series of power *** design and implement an interactive system that supports a set of analytical tasks proposed by domain experts and experienced *** have been conducted with domain experts to illustrate the usability and effectiveness of WaveLines.

关键词： stability visual analysis power grid simulation data

Few-Shot Domain Adaptation for Charge Prediction on Unprofessional Descriptions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Jie Guan, Ziyu Zhao, Wei Jiang, Yue He, Xiaofei State Key Laboratory of Integrated Services Networks School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China State Key Lab of CAD&CG College of Computer Science Zhejiang University Zhejiang Hangzhou310058 China

—Recent works considering professional legal-linguistic style (PLLS) texts have shown promising results on the charge prediction task. However, unprofessional users also show an increasing demand on such a prediction service. There is a clear domain discrepancy between PLLS texts and non-PLLS texts expressed by those laypersons, which degrades the current SOTA models’ performance on non-PLLS texts. A key challenge is the scarcity of non-PLLS data for most charge classes. This paper proposes a novel few-shot domain adaptation (FSDA) method named Disentangled Legal Content for Charge Prediction (DLCCP). Compared with existing FSDA works, which solely perform instance-level alignment without considering the negative impact of text style information existing in latent features, DLCCP (1) disentangles the content and style representations for better domain-invariant legal content learning with carefully designed optimization goals for content and style spaces and, (2) employs the constitutive elements knowledge of charges to extract and align element-level and instance-level content representations simultaneously. We contribute the first publicly available non-PLLS dataset named NCCP for developing layperson-friendly charge prediction models. Experiments on NCCP show the superiority of our methods over competitive baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting