Speaker: Wen Song, Shandong University, China
Date: 17 April 2025
Time: 4:00 - 5:00pm (Beijing Time, UTC+8) [Convert to your local time]
Zoom link: https://vuw.zoom.us/j/95372715200
Wen Song received his Bachelor’s and Master’s degrees from Shandong University, China, and the PhD degree from Nanyang Technological University, Singapore. He is currently an Associate Professor with Shandong University, China. His research interests include artificial intelligence, combinatorial optimization, planning and scheduling. His work on learning driven scheduling received the 2024 IEEE TII outstanding paper reward. He served as an Area Chair/Senior PC for top conferences such as ICML, ICLR and AAAI. He is an IEEE Senior Member.
Combinatorial optimization is one of the core technologies for intelligent decision-making. Traditional solution algorithms rely on expert experience, often entailing high development costs and relatively poor adaptability. Deep learning driven combinatorial optimization methods, leveraging the powerful representation learning capabilities of deep neural networks, aim to automatically acquire problem-specific knowledge from historical data in a data-driven manner to guide the solution process, offering the potential to overcome the limitations of traditional approaches. This talk will introduce the fundamental principles and main paradigms of this emerging research hotspot, along with the speaker's latest advances in the field and some insights into future directions.
Speaker: Ruibin Bai, University of Nottingham Ningbo China
Date: 12 May 2025
Time: 4:00 - 5:00pm (Beijing Time, UTC+8) [Convert to your local time]
Zoom link: TBA
TBA
TBA
Speaker: Fei Liu, City University of Hong Kong
Date: 23 June 2025
Time: 4:00 - 5:00pm (Beijing Time, UTC+8) [Convert to your local time]
Zoom link: https://vuw.zoom.us/j/93516613732
Fei Liu is a Postdoc in Prof Qingfu Zhang’s group (http://optima.cs.cityu.edu.hk/) at the Department of Computer Science, City University of Hong Kong, Hong Kong. He received his BSc degree and MSc degrees from Northwestern Polytechnical University, China in 2017 and 2020, and Ph.D. degree from City University of Hong Kong, Hong Kong in 2025. His main research interests include computational intelligence, optimization, and their applications. Currently, he is working on Large Language Model for Algorithm Design (LLM4AD). He has published 10+ papers in the journal and conference including TEVC, ICML, KDD, AAAI, IJCAI. He has received Champion of the IEEE HK CI Postgraduate Student Research Paper Competition 2024, Second Price (only one) of the IEEE FLAME Competition 2024, Best Paper Nomination at PPSN 2024, Gold Award in the EMO2021 HUAWEI Logistic Competition, and Outstanding Master's Thesis by CSAA in 2020.
Algorithm Design (AD) plays a pivotal role in problem-solving across diverse domains. The emergence of Large Language Models (LLMs) has significantly advanced automation and innovation in this field. We first present a systematic review and taxonomy of the literature on algorithm design utilizing large language models. Next, we introduce Evolution of Heuristic (EoH), an evolutionary framework that integrates LLMs with Evolutionary Computation to facilitate automatic algorithm design. Additionally, we introduce LLM4AD, an open-source, user-friendly platform designed to support algorithm development with large language models. This platform aims to provide modalized tools, methodologies, and tasks, fostering further research and application in the field.
Speaker: Yue Xie, University of Cambridge
Date: 28 July 2025
Time: 10:00 - 11:00am (London Time, UTC+1) [Convert to your local time]
Zoom link: TBA
TBA
TBA
If you have any questions or queries, please email Yi Mei or Fangfang Zhang.
Go to TOP
Go to TOP