PROF. ROMAN SENKERIK

​

​

​Title: Recent advancements in the GenAI-driven design and discovery of algorithms

Abstract: Large language models (LLMs) are transforming how we create and automate AI techniques. We are moving beyond just hyperparameter tuning and automated selection into the automated design and discovery of algorithms, architectures, and end-to-end pipelines that connect ideation with evaluation. This tutorial provides an overview of the rapidly evolving landscape, including frameworks such as EASE, LLaMEA, AlphaEvolve, FunSearch, and emerging AI-driven assistants.
 
Special emphasis will be placed on EASE (Effortless Algorithmic Solution Evolution), which serves as a practical, fully modular framework for iterative closed-loop generation and evaluation. Beyond generating algorithm code, EASE can also create text and graphics iteratively.

​

Prof. Roman Senkerik received his Ph.D. degree in Technical Cybernetics from the Tomas Bata University in Zlin, Czech Republic in 2008. He is currently a full professor at the Tomas Bata University in Zlin, Faculty of Applied Informatics. His research interests include interdisciplinary applications of evolutionary computation, modification and development of evolutionary and swarm based algorithms, computational intelligence, optimization, cyber-security, theory of chaos, emergence and complexity.