Martin Briesch ist derzeit Postdoktorand am Lehrstuhl und forscht zu Themen des maschinellen und evolutionären Lernens. Er hat erfolgreich seine Promotion im Jahr 2026 mit dem Titel „Selected Topics on Machine and Evolutionary Learning“ abgeschlossen und ist seit 2020 am Lehrstuhl von Prof. Dr. Rothlauf als wissenschaftlicher Mitarbeiter beschäftigt. Während seiner Promotion war er außerdem 3 Monate als Gastwissenschaftler am Imperial College London bei Prof. Dr. Antoine Cully. Vorher studierte er Wirtschaftswissenschaften (B.Sc.) von 2014 bis 2017 und Management (M.Sc.) von 2017 bis 2020 an der Johannes Gutenberg Universität Mainz.
Meine Forschungsschwerpunkte sind die Anwendung sowie methodische Entwicklung von Ansätzen aus dem Maschinellen und Evolutionären Lernens. Insbesondere beschäftige ich mich mit Large Language Models (LLMs) und Genetischer Programmierung (GP).
2026
Geiger, A., Briesch, M., Sobania, D., und Rothlauf, F. (2026). ROIDS: Robust Outlier-Aware Informed Down-Sampling.
2025
Sobania, D., Petke, J., Briesch, M., Rothlauf, F. (2025). A Comparison of Large Language Models and Genetic Programming for Program Synthesis. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 29(4), 1434-1448. DOI Author/Publisher URL
Geiger, A., Briesch, M., Sobania, D., Rothlauf, F. (2025). Was Tournament Selection All We Ever Needed? A Critical Reflection on Lexicase Selection. In B. Xue, L. Manzoni, und I. Bakurov (Hrsg.), EuroGP (Bde. 15609, S. 207-223). Springer. Author/Publisher URL
Schaeffer, M., Sobania, D., Briesch, M., et al. (2025). Which kind of experts in which loops? Redefining the relationship between translators, data, and models. 11th Congress of the European Society for Translation Studies (EST), Leeds, United Kingdom, 30 June-3 July 2025.
Sobania, D., Briesch, M., Rothlauf, F. (2025). ImageBreeder: Guiding Diffusion Models with Evolutionary Computation. PROCEEDINGS OF THE 2025 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2025, 463-471. DOI Author/Publisher URL
Zoeten, M. C. de, Hauck, M., Briesch, M., et al. (2025). Let Me Entertain You: On the Bias of Editorial and Algorithmic Recommendations in Public Service Media. In I. Lukovic, S. Bjeladinovic, B. Delibasic, et al. (Hrsg.), ISD. University of Gdańsk, University of Belgrade, Association for Information Systems. Author/Publisher URL
2024
Boldi, R., Briesch, M., Sobania, D., et al. (2024). Informed Down-Sampled Lexicase Selection: Identifying Productive Training Cases for Efficient Problem Solving. EVOLUTIONARY COMPUTATION, 32(4), 307-337. DOI Author/Publisher URL
Boldi, R., Bao, A., Briesch, M., et al. (2024). A Comprehensive Analysis of Down-sampling for Genetic Programming-based Program Synthesis. Proceedings of the Genetic and Evolutionary Computation Conference Companion, 487-490. DOI
Boldi, R., Bao, A., Briesch, M., et al. (2024). Untangling the effects of down-sampling and selection in genetic programming. Artificial Life Conference Proceedings 36, 2024, 88-88.
Briesch, M., Boldi, R., Sobania, D., et al. (2024). Improving Lexicase Selection with Informed Down -Sampling. PROCEEDINGS OF THE 2024 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2024 COMPANION, 25-26. DOI Author/Publisher URL
Sobania, D., Briesch, M., Rothlauf, F. (2024). ComfyGI: Automatic Improvement of Image Generation Workflows. CoRR, abs/2411.14193.
2023
Briesch, M., Sobania, D., Rothlauf, F. (2023). Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop. Author/Publisher URL
Kuhl, E., Zang, C., Esper, J., et al. (2023). Using machine learning on tree-ring data to determine the geographical provenance of historical construction timbers. ECOSPHERE, 14(3). DOI Author/Publisher URL
Boldi, R., Bao, A., Briesch, M., et al. (2023). The Problem Solving Benefits of Down-sampling Vary by Selection Scheme. PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION, 527-530. DOI Author/Publisher URL
Briesch, M., Sobania, D., Rothlauf, F. (2023). On the Trade-Off between Population Size and Number of Generations in GP for Program Synthesis. PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION, 535-538. DOI Author/Publisher URL
Huschens, M., Briesch, M., Sobania, D., Rothlauf, F. (2023). Do you trust ChatGPT?–perceived credibility of human and AI-generated content. arXiv preprint arXiv:2309.02524.
Sobania, D., Briesch, M., Hanna, C., Petke, J. (2023). An Analysis of the Automatic Bug Fixing Performance of ChatGPT. 2023 IEEE/ACM INTERNATIONAL WORKSHOP ON AUTOMATED PROGRAM REPAIR, APR, 23-30. DOI Author/Publisher URL
Sobania, D., Briesch, M., Röchner, P., Rothlauf, F. (2023). MTGP: Combining metamorphic testing and genetic programming. European Conference on Genetic Programming (Part of EvoStar), 324-338.
2022
Briesch, M., Sobania, D., und Rothlauf, F. (2022). The Randomness of Input Data Spaces is an A Priori Predictor for Generalization (Bde. 13404, S. 17-30). DOI Author/Publisher URL
Sobania, D., Briesch, M., und Rothlauf, F. (2022). Choose Your Programming Copilot A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming. PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO’22), 1019-1027. DOI Author/Publisher URL
Sobania, D., Briesch, M., Wittenberg, D., und Rothlauf, F. (2022). Analyzing Optimized Constants in Genetic Programming on a Real-World Regression Problem. PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, 606-607. DOI Author/Publisher URL
Ich betreue momentan folgende Fächer:
- Sommer-Semester 2026: Data Science und Maschinelles Lernen: Einführung und Anwendung (weitere Infos)
Gerne betreue ich auch Masterarbeiten die mit meinen Forschungsfeldern zusammenhängen. Wenden Sie sich dazu bitte mit ersten Themenvorschlägen per E-Mail direkt an mich.
