Skip to content
Technical University of Munich

Anna Bodonhelyi

Research Assistant, PhD Student

Room: 254

Office Hours: nach Vereinbarung

Tel.: +49 89 289 24328

E-Mail: anna.bodonhelyi[at]tum[dot]de

Bio

I am a dedicated Ph.D. candidate at the Technical University of Munich specializing in machine learning, having earned dual master's degrees from the Budapest University of Technology and Economics in Mechatronics and the Technical University of Munich in Robotics, Cognition, Intelligence. With a solid foundation in interdisciplinary fields, in my Ph.D. research, I actively engage in exploring the dynamic realm of human-AI interaction, seeking to enhance the symbiotic relationship between individuals and artificial intelligence through innovative methodologies such as federated learning, computer vision, generative AI, and privacy-enhancing technologies.

Career Development

  • 2016 – 2020: B.Sc. in Mechatronics Engineering at Budapest University of Technology and Economics, Hungary
  • 2018 – 2019: ERASMUS Semester at Karlsruhe Institute of Technology, Germany
  • 2020 – 2022: M.Sc. in Mechatronics Engineering at Budapest University of Technology and Economics, Hungary
  • 2020 – 2023: M.Sc. in Robotics, Cognition, Intelligence at Technical University of Munich, Germany
  • 2023 – now: PhD Candidate at Technical University of Munich, Germany

Research Interests

  • Machine Learning
  • Computer Vision
  • GenAI
  • HCI
  • LLMs

Publications

  • Bodonhelyi, A., Thaqi, E., Özdel, S., Bozkir, E., & Kasneci, E. (2025). From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI '25). Association for Computing Machinery, New York, NY, USA, Article 16, 1–21. doi.org/10.1145/3706598.3713513
  • Bodonhelyi, A., Stegemann-Philipps, C., Sonanini, A., Herschbach, L., Szép, M., Herrmann-Werner, A., Festl-Wietek, T., Kasneci, E., & Holderried, F. (2025). Modeling Challenging Patient Interactions: LLMs for Medical Communication Training.  https://arxiv.org/abs/2503.22250 . Under review for Artificial Intelligence in Medicine
  • Bodonhelyi, A., Bozkir, E., Yang, S., Kasneci, E., & Kasneci, G. (2024). User Intent Recognition and Satisfaction with Large Language Models: A User Study with ChatGPT. arXiv preprint arXiv:2402.02136. arxiv.org/pdf/2402.02136.pdf
  • Wang, M., Bodonhelyi, A., Bozkir, E., & Kasneci, E. (2024, March). TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 14, pp. 15546-15554). https://doi.org/10.1609/aaai.v38i14.29481

Also, check Google Scholar for an up-to-date list.

Outreach Activities

  • 10.23 Organization of WiDS Munich​ event
  • 11.23 TUM EdTech Webinar: "Generative AI in Academia"
  • 02.24 AAAI Poster presenation​ in Vancouver
  • 07.24 Seminar Berufliche Bildung: "Videogeneration with AI"​
  • 08.24 Workshop in Elmau​ :"Kreativ mit KI"
  • 10.24 Workshop in Grundschule am Winthirplatz
  • 10.24 3-day workshop in collaboration with the Roland Berger Stiftung
  • 02.25 Keynote speach: “From Passive Watching to Active Learning: Strengthening proactive participation with LLM-based assistants” at the Automated Assessment of Teaching Effectiveness Using Multimodal Data workshop
  • 04.25 CHI paper presentation: “From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant”
To top