Organized by the IEEE Computational Intelligence Society Shenzhen Chapter.

Activity Aim & Talk

As modern optimization tasks grow in number and diversity, automated algorithm design becomes essential. This talk introduces Meta-Black-Box Optimization (MetaBBO), from early ideas to recent advances, and organizes the field into four paradigms: algorithm selection, algorithm configuration, algorithm generation, and solution manipulation. I will focus on our contributions to algorithm generation along three directions: discovering evolutionary update rules in a symbolic mathematical space; assembling optimizers with parameters in a modular space; and leveraging large language models to synthesize executable optimizer code. To strengthen generalization, we study how to build diverse training task sets and how to learn more effective task and state representations. I will also present the MetaBox platform, which aims to improve the development efficiency and support fair evaluation in the field. I will end with a brief look ahead to key opportunities and open questions.

Meet the Speaker

Yue-Jiao Gong is a Full Professor in the School of Computer Science and Engineering at South China University of Technology (SCUT), China. Her research includes evolutionary computation, deep reinforcement learning, meta-black-box optimization, and their applications in smart cities and intelligent transportation. She has authored over 100 peer-reviewed papers, with more than 60 in ACM and IEEE Transactions and over 50 at leading conferences such as NeurIPS, ICLR, and GECCO. She was named to the Stanford World’s Top 2% Scientists list in the artificial intelligence field. Dr. Gong received the Guangdong Natural Science Fund for Distinguished Young Scholars. She serves as an Associate Editor of IEEE Transactions on Evolutionary Computation, a Senior Program Committee member for AAAI, and the Chair of LEAD 2025.