Yiheng Xiong, M.Sc.

PhD Project:

Robust Deep Learning for Medical Imaging under Domain Shift and Data Scarcity

Yiheng Xiong joined KEMAI in January 2025. He received his M.Sc. in Informatics from the Technical University of Munich in 2024, where he focused on computer vision and deep learning for medical image analysis. He is now pursuing his PhD under the supervision of Prof. Michael Götz, working on developing robust and reliable methods for medical AI.

Research Interests

• Computer Vision
• Deep Learning
• Medical AI

Publications

* denotes equal contribution and † denotes shared last authorship.

Peer-Reviewed

FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
Luisa Gallée, Yiheng Xiong, Meinrad Beer, Michael Götz.
Medical Imaging with Deep Learning (MIDL), 2026 (Oral, Top 8%).
ArXiv / Code

PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images
Yiheng Xiong, Angela Dai.
British Machine Vision Conference (BMVC), 2024 (Oral, Top 3%).
ArXiv / Code / Video / Paper

Prior-RadGraphFormer: A Prior-Knowledge-Enhanced Transformer for Generating Radiology Graphs from X-Rays
Yiheng Xiong*, Jingsong Liu*, Kamilia Zaripova*, Sahand Sharifzadeh, Matthias Keicher†, Nassir Navab†.
MICCAI Workshop on GRaphs in biomedicAl Image anaLysis (GRAIL), 2023.
ArXiv / Code / Paper