This year’s Genetic and Evolutionary Computation Conference (GECCO 2025) in Málaga was a great success! Our chair was represented with three contributions that garnered significant interest.

Best Paper Award for TSGP
We are very proud that the contribution “Transformer Semantic Genetic Programming for Symbolic Regression” by Philipp Anthes, Dominik Sobania, and Franz Rothlauf was honored with the Best Paper Award.
The paper presents an innovative approach to solving symbolic regression problems, employing transformer-based neural networks in genetic programming. By considering solution behavior, the procedure can generate compact models with high predictive quality after just a few iterations.

Evolutionary Image Generation with ImageBreeder
Star Wars goes GECCO – May the force be with you in image generation!
With “ImageBreeder”, Martin Briesch and Dominik Sobania presented a novel approach to evolutionary image generation.
The system combines diffusion models with evolutionary algorithms to algorithmically optimize the visual quality of generated images. The project received considerable attention and shows exciting prospects for fully autonomous image optimization – entirely without human feedback.

Benchmarking of Selection Procedures in Genetic Programming
Alina Geiger presented her benchmark study, recently published in Transactions on Evolutionary Learning and Optimization.
The paper compares the performance of modern Lexicase-based selection procedures (ε‑Lexicase, Batch‑Lexicase, Plexicase) with classical methods such as Tournament Selection and Fitness-Proportionate Selection – each incorporating various downsampling strategies. The results provide valuable insights for the selection and combination of selection and downsampling strategies in genetic programming.

We warmly congratulate all participants on their exciting contributions and are already looking forward to GECCO 2026!