Chair of Software Engineering for Business Information Systems (sebis)​
School of Computation, Information and Technology (CIT)​
​
Technische Universität München (TUM)​
Boltzmannstraße 3,​
85748 Garching, Germany

Phone +49 (89) 289 -17143
Email ibrahim.yurt@tum.de
Room FMI 01.12.036
Office hours: by appointment

_{^{Curriculum Vitae}} 

Ibrahim Ebrar Yurt has been a Research Associate at the Chair of Software Engineering for Business Information Systems at the Technical University of Munich since October 2025. He holds a Bachelor’s degree in Mathematics from Boğaziçi University, where he graduated first in his cohort, and a Master’s degree in Mathematics in Data Science from TUM. During his Master’s studies, he focused on natural language processing and machine learning, gaining industry experience through working student positions in Generative AI and Retrieval-Augmented Generation.

_{^{Research Interests}}

• Information Retrieval & Retrieval-Augmented Generation
• Embedding and Reranker Models for Medical Text
• Evaluation Methodologies for Medical IR and RAG
• Domain Adaptation and Fine-Tuning Strategies for Medical NLP
• Contrastive, Diffusion-Based, and Alternative Training Objectives for NLP

_{^{Open Thesis Topics}}

I do not offer specific thesis topics, but I do offer thesis supervision for motivated master's students. If you would like to pursue a topic related to my research interests, please send me an email with your CV and transcript attached. Possible areas include improving medical RAG systems, developing or fine-tuning embedding and reranking models, evaluating retrieval pipelines, or conducting surveys on medical NLP models, benchmarks, and training techniques.

_^Projects

Aidvice–AI-Based Knowledge Assistant for Cancer Care

The Aidvice AI-driven medical knowledge assistant improves access to complex oncology guidelines by providing personalized, up-to-date, explainable, and understandable information for patients and doctors. It is a question-answering framework that utilizes LLMs, RAG, and automated fact-checking mechanisms.