Research interests:
- Data Quality & Reliability of GenAI outputs
- Building and Evaluating Generative AI Systems for Business Applications
- Evaluation of LLM Agents in Retrieval Systems + Extraction Systems
Short Bio:
I am a PhD candidate in the BMW doctoral program and a Research Associate at the Chair for Strategy and Organization at TUM. My research explores the application of Generative AI across diverse business domains, with a particular focus on the design, development, and evaluation of LLM systems. I am especially interested in data quality, system reliability, and the performance of LLM agents in retrieval and extraction contexts.
Educational background:
- B.Sc. Information Systems (TUM)
- M.Sc. Information Systems (TUM)
Publications:
- Kapsecker, M., Mille, E., Schweizer, F., Klinker, J., Yu, J., Leube, A., & Jonas, S. M. (2025). Facial Landmark Analysis for Detecting Visual Impairment in Mobile LogMAR Test. IEEE Journal of Biomedical and Health Informatics. https://doi.org/10.1109/jbhi.2025.3529288
- Klinker, J., Yu, J., Avezum-Mercer, M., & Jonas, S. (2023). Presenting a Statistical Approach for Transforming Standardized German Traffic Surveys into Origin-Destination Matrices. Proceedings of the 2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST) (pp. 177-186). IEEE. https://doi.org/10.1109/MOST57249.2023.00026
Conference Presentations:
- Klinker, J., Yu, J., Avezum-Mercer, M., & Jonas, S. (2023). Presenting a Statistical Approach for Transforming Standardized German Traffic Surveys into Origin-Destination Matrices. Paper presentation at the 2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)
Work experience:
- Digitalization Cost Engineering @BMW
- Associate Consultant @Simon-Kucher
- Research Assistant Digital Health @TUM
Supervisions:
I also offer additional thesis supervision on topics related to my research interests. Please include your CV and academic transcript in your application.
Room Number: 2556
Email: joe(dot)yu(at)tum(dot)de