Professor Guangjie Han

IEEE Fellow, IET/IEE Fellow, AAIA Fellow

Hohai University, China

Guangjie Han is a professor, currently serving as the Dean of the School of Information Science and Engineering at Hohai University. He is an IEEE Fellow, IET/IEE Fellow, and AAIA Fellow. His main research interests include smart oceans, industrial IoT, artificial intelligence, networks, and security. In recent years, he has published more than 300 high-level SCI journal papers, including over 160 papers in the IEEE/ACM Trans. series, in international journals such as IEEE JSAC, IEEE TMC, IEEE TPDS, and IEEE TCC. His publications have been cited over 26300 times on Google Scholar, with an H-index of 84. He has authored three monographs and translated one book. He has led more than 30 provincial and ministerial-level research projects, including national key R&D programs and national natural science foundation key projects. He has been granted 130 national invention patents and 6 PCT international authorized patents. He has received numerous awards, including the second prize of the China Business Federation Science and Technology Award, the third prize of the Jiangsu Provincial Science and Technology Award, the second prize of the Liaoning Provincial Science and Technology Progress Award, and the Best Paper Award of the IEEE Systems Journal in 2020. For seven consecutive years (2019-2025), he has been listed as one of the top 2% of scientists globally, as well as for the Chinese Highly Cited Researchers list for six consecutive years (2020-2025). Currently, he serves as an associate editor for more than ten international journals, including IEEE TII, IEEE TCCN, IEEE TVT and IEEE Systems.

Speech Title: Underwater Multi-Agent Embodied Intelligence Networks: Research Progress and Perspectives

Abstract: Rapid advances in embodied intelligence are driving underwater intelligent systems from single-agent autonomy toward collective embodied intelligence. Underwater multi-agent systems, such as autonomous underwater vehicle (AUV) clusters, need to continuously sense the ocean environment, learn and make decisions, coordinate through networks, and interact with the physical world. These capabilities form a closed loop of sensing, learning, decision-making, coordination, and action. This loop supports the autonomous execution of complex underwater missions. However, underwater multi-agent systems face many challenges due to the complex ocean environment, limited underwater communication, uncertain sensing, scarce interaction data, changing cluster sizes, and environmental disturbances. These challenges affect embodied perception, efficient learning, scalability, multi-agent coordination, and robust control. To address these challenges, this talk introduces the concept of underwater multi-agent embodied intelligence networks. It considers agents, communication networks, and the ocean environment as parts of a coupled system. Network connections support information exchange, knowledge sharing, and coordinated actions among agents. Embodied interactions further support the emergence and development of collective intelligence. Based on our laboratory's recent research, this presentation reviews advances in embodied perception, efficient embodied learning, scalable embodied decision-making, networked embodied coordination, and robust embodied control for underwater multi-agent systems. This presentation aims to provide a new research perspective on underwater multi-agent systems. It revisits the connections among underwater sensing, communication, learning, decision-making, and control. It also explores how networks and intelligence can be closely integrated to develop underwater collective embodied intelligence. The goal is to support the development of a smart ocean with autonomous sensing, cognition, coordination, and action.

Professor Ying Tan

Peking University, China

Tan Ying, a native of Yingshan, Sichuan Province, PhD in Engineering. He is currently a Professor and Doctoral Supervisor at Peking University, the inventor of the Fireworks Algorithm (FWA), a Member of the National Academy of Artificial Intelligence (NAAI), and an AAIS Fellow, electee of the 100-Talents Program of the Chinese Academy of Sciences in 2005.  His previous academic appointments include Professor at Kyushu University (Japan), Senior Research Scientist at Columbia University (USA), Professor at the University of Science and Technology of China, Research Fellow at the Chinese University of Hong Kong, Professor, Doctoral Supervisor, and Director of the Institute of Intelligent Systems at Electronic Engineering University. His core research interests cover intelligent science, computational intelligence and swarm intelligence, machine learning, big data mining and analytics, as well as their applications in information security, Fintech and related fields. He has presided over more than 30 national-level scientific research projects. He has authored over 20 academic monographs, including Fireworks Algorithm (published by Springer), GPU-based Parallel Implementation of Swarm Intelligence Algorithms (Morgan Kaufmann – Elsevier), and Introduction to Fireworks Algorithm (Science Press). He has also edited 80+ volumes of Springer-Nature LNCS conference proceedings as an Editor-in-Chief. He has published over 450 academic papers and received more than 10 Natural Science Awards at national, Ministry of Education and Beijing municipal levels. He holds over 12 authorized international and national invention patents, together with numerous Best Paper Awards. He serves as Editor-in-Chief, Associate Editor and Editorial Board Member for more than a dozen international journals. He founded and chairs the International Conference on Swarm Intelligence (ICSI), and has acted as General Chair for over 50 international conferences and symposia. He serves as President of the International Society for Swarm and Evolutionary Intelligence, and acts as a review panel expert for multiple international and national science foundations and award programs.

Speech Title: The Progress of Fireworks Algorithm (FWA) & Its Applications

Abstract：Inspired from the collectivebehaviors of many swarm-based creatures in nature or socialphenomena, swarm intelligence (SI) has been received attention and studied extensively, gradually becomes a class of efficiently intelligent optimization methods.Inspired by fireworks’ explosion in air,the so-called fireworks algorithm (FWA) was proposed in 2010.Since then, many improvements and beyond were proposed to increase the efficiency of FWA dramatically, furthermore, a variety of successful applications were reported to enrich the studies of FWA considerably. Inthistalk, the novel swarm intelligence algorithm, i.e., fireworks algorithm, is briefly introducedand reviewed, thenseveraleffectiveimprovedalgorithms arehighlighted,individually. In addition,the multi-objective fireworks algorithm and the graphic processing unit (GPU) basedFWAare alsobrieflypresented, particularly the GPU-basedFWA is able to speed up the optimizationprocess extremely. Extensive experiments onbenchmark functions demonstrate that the improvedalgorithms significantly increase the accuracy of found solutions, yet decrease the running timesharply.Finally, several typical applications ofFWA, in particular, for big-dataapplication, are presented in detail.

Professor Weijia Jia

IEEE Fellow

Beijing Normal University/BNBU, Zhuhai, China

Professor Weijia Jia (IEEE Fellow) is currently the Director of Institute of Artificial Intelligence and Future Networking, and Super Intelligent Computer Center, Beijing Normal University (BNU, Zhuhai); also a Chair Professor at BNBU(UIC), Zhuhai, Guangdong, China. His contributions have been recognized for the research of edge AI, optimal network routing and deployment; vertex cover; anycast and multicast protocols; sensors networking; knowledge relation extractions; NLP and intelligent edge computing. He has over 800 publications in the prestige international journals/conferences and research books and book chapters. He has received the best product awards from the International Science & Tech. Expo (Shenzhen) in 2011/2012 and the 1st Prize of Scientific Research Awards from the Ministry of Education of China in 2017 (list 2), 1st Prize of Shanghai Science and Technology Award (2025, list 4)；2025 China Industry-University-Research Collaboration Innovation Awardand top 2% World Scientists in Stanford-list (2020-2026). 

Speech Title: Open-Loop Agent Tabular QA 

Abstract：The advancement of large language models (LLMs) has enhanced tabular question answering (Tabular QA), yet they struggle with open-domain queries exhibiting underspecified or uncertain expressions. To address this, we introduce Open-Loop Agent QA system that composes of agent workflows with comprehensive benchmark to tackle with open tabular for real estate: (1) a large-scale benchmark with 5K tables and 75K QA pairs; a fine-grained labeling scheme for detailed evaluation; and (2) a dynamic clarification interface that simulates user feedback for interactive assessment. We also propose a multi-agent framework that excels at detecting ambiguities, clarifying them through dialogue, and refining answers; (3) A large-scale instances featuring machine-verifiable supervision for intermediate steps, including structured intent labels, SQL queries, and API calls. We propose a hierarchical agent framework instantiating an under-stand–plan–execute architecture as a strong baseline. By orchestrating a Front-end parser, a planning Supervisor, and execution Specialists, hierarchical-agent effectively integrates heterogeneous evidence. Extensive experiments demonstrate that hierarchical-Agent constitutes a strong baseline and substantiates the necessity of hierarchical collaboration for complex, real-world reasoning tasks.