Title:  Understanding the algorithmic bias of graph neural networks

Abstract:  There is growing interest in learning algorithmic reasoning directly from data. In this talk, we survey recent results on the ability of graph neural networks to express, learn, and generalize algorithmic procedures from finite training data. First, we present a theoretical framework for characterizing when a graph neural network can learn an algorithm in a supervised setting and provably generalize beyond the training distribution. Second, we describe an unsupervised framework for learning to solve the uniform facility location problem with a constant-factor approximation guarantee.

Bio: Christopher Morris studied Computer Science at TU Dortmund University, Germany. In 2019, after a short stint at Stanford University, he completed his Ph.D. at TU Dortmund, focusing on machine learning for graph and relational data. He then spent one year as a postdoctoral fellow at Polytechnique Montréal in the Department of Mathematical and Industrial Engineering, followed by a postdoctoral position in the Computer Science Department at McGill University and as a member of Mila – Quebec AI Institute. In June 2022, he joined RWTH Aachen University, Germany, as a tenure-track assistant professor in the Computer Science Department and was promoted to full professor in  December 2025.

Title:  Automated Algorithm Design with Large Language Model

Abstract: Algorithm design plays a fundamental role across many fields. Recent advances in Large Language Models (LLMs) are creating new opportunities to automate and accelerate this traditionally human-driven process. In this talk, I will first provide an overview of automated algorithm design with LLMs. I will then introduce Evolution of Heuristics (EoH), an evolutionary framework that combines LLMs with evolutionary search to automatically discover and improve algorithms. I will also discuss recent advances and applications across different domains, and conclude with key challenges and future research directions toward more general and autonomous algorithm design.

Bio: Dr. Fei Liu is a Postdoc researcher in the Department of Physics, University of Zurich and the Department of Mathematics, ETH Zurich, working with Prof. Nicola Serra and Prof. Alessio Figalli. Previously he was a Postdoc Fellow in Prof. Qingfu Zhang's Group, Department of Computer Science, City University of Hong Kong. He completed his PhD at CityU supervised by Prof. Qingfu Zhang, and his master's and bachelor's degrees at Northwestern Polytechnical University supervised by Prof. Zhonghua Han. His research interests include automatic algorithm design, artificial intelligence, optimization algorithms, and their applications to real-world problems..