Chengzhi Shen

About

I am Chengzhi Shen, a PhD student at the Chair of AI in Healthcare and Medicine at the Technical University of Munich (TUM), supervised by Prof. Dr. Daniel Rueckert. I work closely with Dr. Jiazhen Pan and Dr. Chen (Cherise) Chen. My research focuses on trustworthy AI, multimodal large models, and agentic systems for medical applications.

Before my PhD, I worked as a Machine Learning Algorithm Engineer at Alibaba Taobao Tmall Group in Hangzhou, where I focused on post-training omni-modal large models based on Qwen series models. I received my M.Sc. in Biomedical Computing from TUM in 2024.

Multimodal and Omni-modal Large Models Agentic Systems Trustworthy AI AI for Healthcare

News

2026.05 Our work RealICU is out!
2026.03 I was super excited to give a talk on "Research in Industry" during our lab retreat in Austria.
2026.01 🚀 Start my PhD at Prof. Dr. Daniel Rueckert's lab!
2024.08 Join Alibaba Group as a Machine Learning Algorithm Engineer.
2024.08 🎉 Finish my master's degree in Biomedical Computing at TUM!

Publications

For the full publication list, please visit my Google Scholar.

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

Chengzhi Shen, Weixiang Shen, Tobias Susetzky, Chen (Cherise)Chen, Jun Li, Yuyuan Liu, Xuepeng Zhang, Zhenyu Gong, Daniel Rueckert, Jiazhen Pan

arXiv 2026

Paper Project Page Code

MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows

Weixiang Shen, Chengzhi Shen, Yanzhu Hu, Che Liu, Junde Wu, Jiayuan Zhu, Xiao Han, Zongyue Li, Jingpei Wu, Min Xu, Daguang Xu, Yueming Jin, Benedikt Wiestler, Daniel Rueckert, Jiazhen Pan

arXiv 2026

Paper

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu

CVPR 2024

Paper Project Page Code

Spatiotemporal Representation Learning for Short and Long Medical Image Time Series

Chengzhi Shen, Martin J. Menten, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Hendrik Scholl, Sobha Sivaprasad, Andrew Lotery, Daniel Rueckert, Paul Hager, Robbie Holland

MICCAI 2024

Paper Code

SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis

Azade Farshad, Yousef Yeganeh, Yu Chi, Chengzhi Shen, Björn Ommer, Nassir Navab

ICCV Workshop 2023

Paper

Background

2026 – Doctoral Candidate
Technical University of Munich, Germany

2024 – 26 Machine Learning Engineer
Alibaba Group, China

2021 – 24 M.Sc. Biomedical Computing
Technical University of Munich, Germany

Honors

2024 Deutschlandstipendium (Germany Scholarship)
2023 Deutschlandstipendium (Germany Scholarship)
2021 University Principal’s Award (top 1%) 大学成就奖
2018 National Scholarship (top 1%) 国家奖学金

Talks

2026.03 Research in Industry - My experience at Alibaba, Lab Retreat, Austria

Services

Reviewer at ICCV Workshop on Scene Graphs and Graph Representation Learning
UN Online Volunteer