Big Data WS-2
The application of Multimodal Large models
多模态大语言模型的应用
2025年IEEE第三届大数据与数据挖掘国际会议（IEEE BDDM 2025）将于2025年12月12日-12月14日在湖南衡阳召开。会议由IEEE中国联合会、南华大学、中南大学联合主办，湖南工学院、AC学术平台协办。会议录用的论文将以会议论文集形式提交出版，收录至IEEE Xplore，并提交 EI Compendex 和 Scopus 数据库。
中国电子科学研究院郭庆浪副教授、金昊副教授受邀担任本次会议Big Data方向Workshop Chair，组建Workshop 2, 并将于会议期间就“多模态大语言模型的应用”进行研究与探讨，欢迎各位专家学者以投稿、参会、学者报告、海报展示等方式加入Workshop 2。
Big Data WS 2 专属投稿链接（ 投稿请备注“论文标题+WS 2”）：
（投稿及参会方式见文末）
（▲扫描二维码登记参会）
Big Data Workshop 2 简介
Summary
The advent of Multimodal Large Models (MMLMs) has ushered in a new era of artificial intelligence, fundamentally transforming our interactions with technology. Our workshop, "Applications of Multimodal Large Models," will provide a comprehensive exploration of MMLMs' capabilities and their applications in various fields, including law, smart home technology, and intelligent security.
These models have made significant progress in natural language processing (NLP) and multimodal interaction, advancing text generation, multimodal agent development, handling multiple visual tasks, and multimodal generation capabilities. For example, multimodal agents can understand various input forms such as voice, text, and images, and provide intelligent responses. Multimodal generation capabilities have also shown great potential in applications like text-to-image and video generation.
The workshop will cover the following topics:
Multimodal Agents and Visual Tasks: Exploring the development of multimodal agents and their applications in smart home technology, autonomous driving, and other scenarios, as well as MMLMs' capabilities in visual tasks such as image classification and object detection.
Multimodal Generation Capabilities: Sharing the latest advancements of MMLMs in text-to-image, video generation, and other related fields.
Integration of Knowledge Graphs with MMLMs: Discussing how knowledge graphs enhance the reasoning and answer-generation capabilities of MMLMs.
Challenges and Ethical Considerations: Analyzing the limitations of current MMLMs, including data privacy, bias, and ethical issues.
Hands-on Experience: Participants will have the opportunity to experience MMLMs and related technologies firsthand.
Led by experts in the field of multimodal large models, this workshop is suitable for professionals looking to leverage MMLMs as well as enthusiasts interested in AI. Join us to explore the future of multimodal artificial intelligence.
Keywords
Multimodal Large Models,Agent,Integration of Knowledge Graphs with MMLMs
Chairs
Assoc. Pro. Qinglang Guo
China Academic of Electronics and Information Technology
Dr. Qinglang Guo , who holds a Ph.D. from the University of Science and Technology of China, is a Senior Engineer and currently serves as the Director of the Artificial Intelligence Innovation Center at the National Engineering Research Center of the China Academy of Electronics and Information Technology. He has participated in major national projects and planning efforts, including the construction planning and evaluation of the nationwide integrated public security system, and the city-level social governance modernization pilot construction planning and evaluation organized by the Central Political and Legal Affairs Commission. Dr. Guo has led or participated in seven major projects, such as national science and technology key projects, key social governance research and development programs, the Joint Fund of Enterprise and the National Natural Science Foundation, and the Equipment Pre-Research Fund of the Central Military Commission. He has published over ten academic papers, applied for more than ten invention patents and software copyrights, and contributed to the development of seven industry standards.
Assoc. Pro. Hao Jin
China Academic of Electronics and Information Technology
Hao Jin received the Ph.D. degree from Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, in 2018. She is currently a Senior Engineer in National Engineering Research Center for Public Safety Risk Perception and Control by Big Data (RPP), China Academic of Electronics and Information Technology. Her main research interests are artificial intelligence and big data. She has published over 20 high-level academic papers indexed in SCI/EI.
征稿主题
集中但不限于以下领域：
大数据：大数据分析、人工智能、大数据网络技术、大数据搜索算法和系统、分布式和点对点搜索、基于大数据的机器学习、大数据可视化分析。
数据挖掘：数据挖掘基础、数据挖掘的挑战、并行和分布式数据挖掘算法、数据流挖掘、图挖掘、空间数据挖掘、文本/视频/多媒体数据挖掘、序列处理与分析、网络挖掘、高性能数据挖掘算法、关联挖掘、基准测试和评估、交互式数据挖掘、数据挖掘就绪结构和预处理、数据挖掘可视化、数据挖掘中的信息隐藏、安全和隐私、挖掘算法的竞争分析、物联网挖掘、个性化和推荐系统、使用小样本网络数据的深度学习、知识图谱。
参与形式
1.Committee
作为大会主席、指导主席或技术主席、TPC等身份参会支持，在会议技术层面上指导把关，负责一部分同行评审环节，组委会将颁发荣誉证书。Committee申请需提供个人学术简历。
2.Reviewer
作为会议的审稿专家参与支持，负责在专业领域内对稿件进行同行评审，组委会将颁发审稿专家证书。Reviewer申请需提供个人学术简历。
3.Workshop
针对会议主题组建workshop，并邀请相同研究领域的专家、学者加入，以分论坛形式展开研讨。注：研讨会形式可同时进行论文投稿、口头报告、听众参加，时长和具体流程可酌情而定。Workshop Chair申请需要提供个人学术简历。
4.Presenter
(1)口头报告：在大会上就报告人目前的研究等进行口头英文学术报告（不需要投稿），时长约10-15分钟。
(2)书面论文报告：在大会征稿主题范围内提交相关领域英文科技论文，评审通过后提交注册并收录到会议论文集。
(3)海报展示：投稿论文除进行现场或线上口头报告外，还可选择现场海报展示，将文章关键成果及摘要展示给现场参会嘉宾。
5.Audience
作为听众参加线下会议的报告分享及活动交流。
奖项介绍
1. IEEE BBDM 2025会议设置了最佳workshop组织奖、优秀论文奖、最佳口头报告奖、最佳海报展示奖、最佳审稿人奖、分论坛主持人奖，所有奖项将在会议当天公布。
2. 参与本届大会的Workshop Chair将享有被优先推举作为下届学术委员会委员、主讲、主席等权利。
投稿指南
1. 请至会议官网：
http://www.icbddm.org/ 下载论文模板。
2. 投稿链接：
https://ocs.academicenter.com/submission/stepone?conf_id=1924286850383384576
3. 请根据以下几点准备您的论文：
（1）论文必须是全英文稿件，非纯综述类，应具有学术或实用推广价值，并且未在国内外学术期刊或会议发表过。
（2）摘要、关键词和结论部分需体现会议主题，不接受教育类、法律类、金融经管类等社科类稿件，文章主要收录技术型的文章，需要有方法、图表、实验数据和结果，且满足科技论文的基本规范和要求。
（3）作者可通过Crossref/Ithenticate查重，总体重复率不得超过25%（含参考文献），单项不超过4%。
（4）文章页面需在4-5页（双栏），正文内容（不含参考文献）需满4页，全文（含参考文献）超过5页需缴纳超页费。
4. 投稿后7-15个工作日内反馈审稿意见或录用通知。
5. 收到录用通知后在5个工作日内完成论文注册。
往届会议情况：
IEEE BDDM 2025已成功申请IEEE冠名，由IEEE北京分会赞助。投稿的论文都必须经过2-3位组委会专家审稿，录用并完成注册的文章将以会议论文集形式提交出版，收录至IEEE Xplore，并提交EI Compendex和Scopus数据库。
第一届、第二届BDDM均已成功检索。
组委会联系方式：
Tel/WeChat：18075175128（唐老师）
