DNAS Study Group

Memory-Driven Complex System Al Modeling Methods and Applications

Date & Time

Date: Thursday, Oct 15, 2026

Time: 11:30 AM – 12:30 PM

Venue: IB 1012

Speaker

Dr. Qunxi Zhu

Young Principal Investigator, Research Institute of Intelligent Complex Systems (IICS), Fudan University, China

Abstract:

How can artificial intelligence be endowed with memory to better understand and simulate complex systems in the real world? This is the central question to be explored in this presentation. The talk will begin by providing an overview of the research background in complex systems, briefly reviewing mainstream methodological frameworks and their current applications. It will then focus on the memory-driven paradigm, systematically introducing progress made by their team in this area and demonstrating its effectiveness in enhancing complex system modeling and identification from theoretical, methodological, and application perspectives. Finally, the presentation will discuss potential pathways and future trends in the intersection of complex systems and artificial intelligence.

摘要

如何赋予人工智能以记忆，使其能够更好地理解和模拟现实世界中的复杂系统？这是本次报告要探讨的核心问题。报告首先从复杂系统研究背景出发，简要回顾主流方法论框架及其当前应用。随后，报告将聚焦记忆驱动范式，系统介绍本团队在此方向上的一些进展，并从理论、方法和应用角度展示其在增强复杂系统建模与辨识方面的有效性。最后，报告将讨论复杂系统与人工智能交叉领域的潜在路径与未来趋势。

Bio

Qunxi Zhu is a Young Principal Investigator at Research Institute of Intelligent Complex Systems (IICS) (智能复杂体系基础理论与关键技术实验室), Fudan University, China. He graduated as a PhD in 2021 from the School of Mathematical Sciences at Fudan University under the supervision of Professor Wei Lin. His research focuses on the forefront of theoretical and methodological studies in complex systems and machine learning. He has made significant contributions in areas such as complex system modeling, reconstruction, prediction, intelligent control, and machine learning driven by complex systems. His research findings have been published in more than 20 papers as the first or corresponding author in international journals such as Nature Communications, Research, IEEE TAC, SIAM-CON, PRResearch/E, and at leading artificial intelligence conferences like ICML, ICLR, and NeurIPS.

He also serves as the executive editor of AIMS’s new journal DCDS-Intelligence and has been selected for prestigious programs including the Shanghai Rising Stars Program, Shanghai Super Postdoctoral Incentive Program, the “Mount Everest” Young Scholars Program of the Ministry of Education’s Brain Science Frontier Center, and Fudan University’s “Outstanding Academic Talent” Cultivation Program.

Bio

朱群喜, 复旦大学智能复杂体系实验室青年研究员。2021年博士毕业于复旦大学数学科学学院, 师从林伟教授。致力于复杂系统和机器学习前沿的理论与方法研究, 在复杂系统建模、重构、预测与智能调控以及复杂系统驱动的机器学习领域做出了一系列工作, 相关成果以第一或通讯作者在Nature Communications, Research, IEEE TAC, SIAM-CON, PRResearch/E等国际期刊和ICML, ICLR, NeurIPS等人工智能会议发表文章20余篇。担任/获AIMS最新期刊 DCDS- Intelligence执行主编, 上海市启明星扬帆计划, 上海市超级博士后激励计划, 教育部脑科学前沿中心“珠峰”青年学者计划，复旦大学“卓学优秀人才”培育计划等。