The Special Session on Intelligent Drive Data: The Fusion Revolution of Artificial Intelligence and Big Data aims to gather researchers and practitioners from academia and industry to explore how data-centric artificial intelligence is reshaping intelligent systems and decision-making. As data volumes, modalities, and acquisition speeds continue to grow explosively, the tight integration of AI algorithms with large-scale, high-quality data has become the core driving force behind breakthroughs in perception, prediction, optimization, and autonomy. This session focuses on how to transform raw, heterogeneous data into actionable intelligence that can effectively drive complex systems in dynamic and uncertain environments.
The session seeks contributions that span foundational theories, key technologies, and real-world applications of AI–big data fusion. Topics include intelligent data acquisition and governance, scalable learning architectures, multimodal data fusion, real-time analytics for autonomous systems, and trustworthy, secure, and interpretable AI in data-intensive scenarios. Application domains of interest range from autonomous driving, intelligent transportation and logistics, smart manufacturing and industrial IoT, to healthcare, finance, and urban computing. By bridging data engineering, machine learning, and domain expertise, this special session aims to advance the next generation of “intelligent drive data” paradigms and promote cross-disciplinary collaboration.
“智驱数据：人工智能与大数据的融合革命”专题论坛旨在汇聚学术界与工业界的研究人员和实践者，系统探讨以数据为驱动力的人工智能如何重塑智能系统与决策模式。随着数据规模的指数级增长以及多模态感知与采集技术的快速发展，人工智能算法与大数据资源的深度融合，正成为智能感知、预测分析、优化控制与自主决策等能力跃迁的关键。本专题将围绕如何将海量、异构、非结构化的数据高效转化为可解释、可落地、可迭代演化的“智驱数据”展开，聚焦智能数据采集与治理、可扩展学习架构、多模态数据融合、面向自主系统的实时分析，以及面向高风险场景的可信、安全与隐私保护等前沿问题。论坛也欢迎在自动驾驶与智能交通、工业互联网与智能制造、智慧医疗与金融科技、智慧城市与时空大数据等典型应用领域的最新研究与实践成果，以期推动人工智能与大数据的深度耦合和多学科交叉创新，驱动新一轮数据智能革命。
Topics of interest include but are not limited to:
1. Data-Centric AI and Intelligent Data Engineering | 数据中心人工智能与智能数据工程
- Data governance, cleaning, labeling, and quality control for AI algorithms 面向人工智能算法的数据治理、清洗、标注与质量控制
- Data lifecycle management, integration, and knowledge graph construction 数据全生命周期管理、集成与知识图谱构建
2. Big Data–Driven Learning Paradigms | 大数据驱动的学习范式
- Self-supervised, weakly supervised, and foundation models trained on large-scale data 面向大规模数据的自监督、弱监督与基础模型训练
- Data-centric model design, optimization, and evaluation 数据中心的模型设计、优化与评估方法
3. Multimodal and Heterogeneous Data Fusion | 多模态与异构数据融合
- Fusion of sensor, spatiotemporal, graph, and unstructured data 传感器、时空、图结构与非结构化数据的融合技术
- Representation learning for heterogeneous, dynamic, and high-dimensional data 面向异构、动态与高维数据的表征学习方法
4. Real-Time Analytics and Streaming Intelligence | 实时分析与流式智能
- Online learning and streaming data mining for dynamic environments 面向动态环境的在线学习与流数据挖掘
- Edge–cloud collaborative intelligence and low-latency decision systems 云边协同智能与低时延决策系统
5. Data-Driven Intelligent Decision-Making and Control | 数据驱动的智能决策与控制
- Data-driven forecasting, optimization, and planning in complex systems 面向复杂系统的预测、优化与规划方法
- Reinforcement learning, digital twins, and simulation-based decision support 强化学习、数字孪生与仿真决策支持技术
6. Trustworthy, Secure, and Privacy-Preserving Data Intelligence | 可信、安全与隐私保护的数据智能
- Robust, interpretable, and fair models in data-intensive scenarios 面向数据密集场景的鲁棒、可解释与公平性模型
- Privacy-preserving learning, federated analytics, and secure data sharing 隐私保护学习、联邦分析与安全数据共享机制
7. Systems, Platforms, and Benchmarks for Intelligent Drive Data | 智驱数据系统平台与基准体系
- Architectures and systems for large-scale AI–big data fusion 支撑人工智能与大数据融合的大规模系统与架构设计
- Open datasets, benchmarks, and evaluation metrics for intelligent drive data 面向智驱数据的开放数据集、基准测试与评测指标体系
8. Applications of Intelligent Drive Data | 智驱数据的应用实践
- Autonomous driving, intelligent transportation, and smart logistics 自动驾驶、智能交通与智慧物流应用
- Smart manufacturing and industrial IoT 智能制造与工业互联网场景
- Healthcare, finance, and smart city data intelligence 智慧医疗、金融科技与智慧城市数据智能应用
9. Human-in-the-Loop and Interactive Data Intelligence | 人在回路与交互式数据智能
- Human-in-the-loop data curation, labeling, and decision support 人在回路的数据筛选、标注与决策支持
- Visualization and interactive analytics for large-scale, complex data 面向大规模复杂数据的可视化与交互分析技术
Chair: Dr. Ziyu Jia, Institute of Automation, Chinese Academy of Sciences, China
Ziyu Jia is an Assistant Professor at the Institute of Automation, Chinese Academy of Sciences. His research focuses on time-series analysis methods and their applications in health and medicine, including multimodal affective computing, sleep stage classification, and brain-computer interfaces. He has published over 50 peer-reviewed papers in venues such as IEEE Transactions on Affective Computing, IEEE Transactions on Multimedia, IEEE Transactions on Neural Systems and Rehabilitation Engineering, KDD, and ICLR. Dr. Jia currently serves as an Associate Editor or Editorial Board Member for prestigious journals including IEEE Transactions on Affective Computing and Information Fusion, and he is an Area Chair for major AI and machine learning conferences such as IJCAI and IJCNN. In addition to his academic contributions, Dr. Jia has extensive industry experience, having successfully led multiple R\&D projects and secured several patents. He has received numerous honors, including the MSRA StarTrack Award, and the CIE Young Talent Award.
Paper/Abstract Submission Instructions
1. Word Template:
Formatting.doc (文章模板)
2. Paper submission link for BDAI2026 is at:
Electronic Submission System (投稿链接)
3. Full Paper (Presentation and Publication)
Accepted full paper will be invited to give the oral presentation at the conference and be published in the conference proceeding.