News

For almost two months, Franz Rothlauf was a Visiting Professor at the UCD Natural Computing Research & Applications Group in Dublin as part of the celebration of NCRA's 20th anniversary. The NCRA group was founded in 2006 by Prof. Anthony Brabazon and Prof. Michael O’Neill, who both kindly hosted Franz during his stay.

Franz gave several talks on evolutionary computation and machine learning and enjoyed the intense discussions at UCD, particularly with Michael O’Neill and the members of his group.

It was an inspiring and pleasant stay at the Smurfit Business School, and Franz is very grateful for the invitation to Dublin.

We are proud to announce that Clarissa Krämer has been accepted as a Junior Fellow in the Gutenberg Academy Fellows Program at Johannes Gutenberg University Mainz.

The Gutenberg Academy Fellows Program brings together outstanding doctoral researchers and connects them with distinguished JGU scholars as well as leading figures from business, politics, and culture. Through financial support and a tailored sponsorship and mentoring model, Junior Fellows receive targeted guidance and encouragement on their academic career paths.

We congratulate Clarissa on this achievement and wish her an inspiring and successful time in the program.

Our team warmly congratulates Dr. Dominik Sobania on his new position as junior professor (W1 t.t. W3) for ‘Generative Artificial Intelligence in Software Engineering’ at the University of Duisburg-Essen. Dominik has held the new professorship at the University of Duisburg-Essen since 1 January 2025.

Dr. Sobania worked as a research assistant and postdoctoral lecturer at our chair from April 2017 to December 2025. During this time, he had a significant impact on and further developed the chair's research and teaching activities.
He defended his dissertation in December 2022 with outstanding success. Since then, he has made an extremely valuable contribution to research and teaching.

His work is characterised in particular by high scientific quality, methodological depth and a strong application orientation. In addition, he has been continuously involved in supervising students, theses and the further development of courses.

With his appointment, the University of Duisburg-Essen gains a scientist with outstanding academic achievements and a forward-looking research profile in the field of generative AI and software engineering.

We would like to express our sincere thanks for the many years of successful cooperation and wish Dominik every success, joy and all the best in his new academic role.

Towards the end of his doctoral studies, Martin Briesch completed a three-month research stay at the Adaptive & Intelligent Robotics Lab headed by Prof. Antoine Cully at Imperial College London.
As part of his research work there, he focused on the combination of large language models (LLMs) and evolutionary methods.
We wish Martin every success for his research stay and looking forward to the new ideas he will bring back from London.

 

This year’s Genetic and Evolutionary Computation Conference (GECCO 2025) in Málaga was a complete success. Our research group was represented with three contributions, all of which attracted significant interest.

Best Paper Award for TSGP
We are very proud of the Best Paper Award for the contribution “Transformer Semantic Genetic Programming for Symbolic Regression” by Philipp Anthes, Dominik Sobania, and Franz Rothlauf.
The paper presents an innovative approach that solves symbolic regression problems by integrating transformer-based neural networks into genetic programming. By taking solution behavior into account, the method can produce compact models with strong predictive performance after only a few iterations.

 

Evolutionary Image Generation with ImageBreeder

Star Wars goes GECCO – May the force be with your image generation!
Martin Briesch and Dominik Sobania presented ImageBreeder, 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 attracted significant attention and shows promising potential for fully autonomous image optimization—without any human feedback.

 

Benchmarking Selection Methods in Genetic Programming
Alina Geiger presented her recently published benchmark study in Transactions on Evolutionary Learning and Optimization.
The study compares the performance of modern Lexicase-based selection methods (ε‑Lexicase, Batch‑Lexicase, Plexicase) with traditional methods like Tournament Selection and Fitness-Proportionate Selection—each combined with various downsampling strategies. The results offer valuable insights for choosing and combining selection and downsampling strategies in genetic programming.
We sincerely congratulate everyone involved on their contributions and are already looking forward to GECCO 2026!

We’re happy to share that our team won the Best Poster Award at EvoStar 2025 in Trieste, Italy!

Our paper, “Was Tournament Selection All We Ever Needed? A Critical Reflection on Lexicase Selection”, took a fresh look at how we select individuals in genetic programming. We found that tournament selection, when combined with down-sampling, performs similar to lexicase selection while being more efficiently!

Thanks to Alina Geiger and Martin Briesch who represented us in Trieste and presented the poster.

You can check out the paper here if you’re curious about the details.

Congratulations to Clarissa Krämer (MSc.), Susanne Schmitt (MSc.), and Prof. Dr. Franz Rothlauf on receiving the Best Student Paper Award at the Medical Informatics Europe (MIE) Conference in Glasgow, Scotland, from May 19-21, 2025.

Their award-winning paper, "Using Machine Learning for the Fusion of Tumor Records on a Real-World Dataset" focuses on consolidating multiple records describing the same tumor into a single record for each tumor. They used an artificial neural network and compared its performance with that of a deterministic, rule-based approach. They used a tabular, real-world dataset that included colorectal, breast, and prostate cancer.

Key findings were that

• Artificial Neural Networks outperform the deterministic rule-based approach.
• The performance depends on the number of features and the distribution of data.
• The predictive performance increases with a lower number of categories within a variable and a more balanced dataset.

Read the paper here: https://pubmed.ncbi.nlm.nih.gov/40380540/

 

We are happy to announce our Sustainable Aviation Day as part of the Airline Strategies lecture on Friday, April 11, 2025.

Sustainability has become a major strategic challenge for the airline industry. High uncertainties regarding technological advancements and regulatory changes make long-term strategies and their financing increasingly complex.

At the event, internationally renowned experts from academia, finance, regulation and the industry will discuss:

• The role of science in developing sustainable aviation strategies.
• Policies related to sustainability in aviation.
• Whether there is a single best strategy for making aviation more sustainable.

The event will take place on Friday, April 11, 2025, starting at 9:00 AM (CEST) in room 00 135 RW 2 in ReWi I and online via Microsoft Teams as a hybrid series of one-hour online lectures.

Our special thanks go to Lufthansa Frankfurt, SMBC Aviation Capital Dublin, UCL London, Cirium Risk Data London, EU Commission – Directorate General Clima, Arena Aviation Capital Amsterdam, Scripps Institution of Oceanography - UC San Diego, Boeing Seattle and Impact on sustainable aviation e.V. Frankfurt am Main for their support in making this event possible.

We look forward to your participation.

Register until Tuesday, April 8, 2025 using the following link: https://zukunft.uni-mainz.de/sustanable-aviation/

In 2024, Prof. Dr. Franz Rothlauf received the SIGEVO Outstanding Contribution Award, which recognizes remarkable contributions to Evolutionary Computation (EC) when evaluated over a sustained period of at least 15 years. These contributions can include technical innovations, publications, leadership, teaching, mentoring, and service to the EC community. To celebrate these distinctions, Franz (as well as Anne Auger) kindly answered some questions reflecting on their contributions and views on evolutionary computation as well as their advice to young researchers in the field.

The full interview can be found in the newsletter of SIGEVO:

https://evolution.sigevo.org/issues/HTML/sigevolution-17-4/index.html

In July 2024, Franz Rothlauf has been awarded with the ACM SIGEVO Outstanding Contribution Award. The awards goes to Professor Rothlauf in recognition of his fundamental and influential research on solution representations in evolutionary computation and of his extraordinary servie to ACM SIGEVO. The awards carries a monetary value of $1,000 and a plaque contributed by SIGEVO.

Further details on this prestigious award can be found at https://sig.sigevo.org/index.html/tiki-index.php?page=ACM%20SIGEVO%20Outstanding%20Contribution%20Award