Yitong Li

Ph.D. Student @ Technical University of Munich, Germany

About me

I am a Ph.D. student at the lab for AI in Medical Imaging (AI-Med) at the Technical University of Munich, Germany, supervised by Prof. Christian Wachinger, and mentored by Prof. Björn Ommer. I am affiliated with MCML and relAI.

My research passion lies at the intersection of computer science, medicine, and 3D computer vision, developing cutting-edge, trustworthy AI tools for medical applications, particularly in generative models, self-supervised learning, and multi-modal learning.

News

Aug 2026Our paper on 3D CT report generation was accepted to EMNLP 2026 main conference.
Aug 2026Our paper on conditional diffusion for 3D CT reconstruction was accepted to BMVC 2026.
Jul 2026Our paper on diffusion bridge networks simulate clinical-grade PET was accepted to The Lancet Medical Imaging & Theranostics (in press).
Jun 2026I started my internship at Zillow Group Inc as an AI Applied Scientist in Generative Computer Vision.
May 2026Our paper on translating MRI to PET through conditional diffusion models was accepted to Medical Image Analysis (IF 14.0).
Feb 2025Our paper on 3D shape-to-image brownian bridge diffusion was accepted to IPMI 2025.
Oct 2024Our paper DiaMond was accepted to WACV 2025 for an oral presentation.
Sept 2024Our paper Stable-Pose was accepted to NeurIPS 2024.
May 2024Our paper PASTA was early-accepted to MICCAI 2024 (top 11%).
Jan 2024Our paper Triplet Training was accepted to MIDL 2024 for an oral presentation.

Selected Publications

The Lancet MIT clean-usnob

Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics

Yitong Li, Ralph Buchert, Benita Schmitz-Koep, Timo Grimmer, Björn Ommer, Dennis M. Hedderich*, Igor Yakushev*, Christian Wachinger*.

(* Equal Advising)

The Lancet Medical Imaging & Theranostics (In press), 2026.

project page paper code

EMNLP 26

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation

Tom Maye-Lasserre*, Yitong Li*, Bailiang Jian*, Morteza Ghahremani, Benedikt Wiestler, Christian Wachinger.

(* Equal Contribution)

EMNLP (Conference on Empirical Methods in Natural Language Processing), 2026.

paper code

BMVC 26

Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

Martin Rath*, Morteza Ghahremani*, Yitong Li*, Ashkan Taghipour, Marcus Makowski, Christian Wachinger.

(* Equal Contribution)

BMVC (British Machine Vision Conference), 2026.

paper code

MedIA

Translating MRI to PET through Conditional Diffusion Models with Enhanced Pathology Awareness

Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger.

Medical Image Analysis (Impact factor: 14.0), 2026.

paper code

Preprint

Cortex-Grounded Diffusion Models for Brain Image Generation

Fabian Bongratz*, Yitong Li*, Sama Elbaroudy, Christian Wachinger.

(* Equal Contribution)

paper code

Preprint

Adapting Foundation Vision-Language Models to Medical Diagnosis via Query-Driven Expert Bridging

Yitong Li*, Morteza Ghahremani*, Christian Wachinger.

(* Equal Contribution)

paper code

IPMI 25

3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces

Fabian Bongratz*, Yitong Li*, Sama Elbaroudy, Christian Wachinger.

(* Equal Contribution)

IPMI (Information Processing in Medical Imaging), 2025.

paper code

WACV 25

DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET

Yitong Li, Morteza Ghahremani, Youssef Wally, Christian Wachinger.

WACV (IEEE/CVF Winter Conference on Applications of Computer Vision), 2025.

Oral presentation

paper code

NeurIPS 24 clean-usnob

Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation

Jiajun Wang*, Morteza Ghahremani*, Yitong Li*, Björn Ommer, Christian Wachinger.

(* Equal Contribution)

NeurIPS (Conference on Neural Information Processing Systems), 2024.

paper code

MICCAI 24

PASTA: Pathology-Aware MRI to PET Cross-Modal Translation with Diffusion Models

Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger.

MICCAI (International Conference On Medical Image Computing & Computer Assisted Intervention), 2024.

Early Accept, top 11%

paper code

MIDL 24

From Barlow Twins to Triplet Training: Differentiating Dementia with Limited Data

Yitong Li*, Tom Nuno Wolf*, Sebastian Pölsterl, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger.

(* Equal Contribution)

MIDL (Medical Imaging with Deep Learning), 2024.

Oral presentation

paper OpenReview code

CVPR 23

On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai, Nikolas Brasch, Yitong Li, Yannick Verdie, Jifei Song, Yiren Zhou, Anil Armagan, Slobodan Ilic, Ales Leonardis, Nassir Navab, Benjamin Busam.

CVPR (IEEE/CVF Conference on Computer Vision and Pattern Recognition), 2023.

paper code

ECCV 22

Polarimetric Pose Prediction

Daoyi Gao*, Yitong Li*, Patrick Ruhkamp*, Iuliia Skobleva*, Magdalena Wysock*, HyunJun Jung, Pengyuan Wang, Arturo Guridi, Nassir Navab, Benjamin Busam.

(* Equal Contribution)

ECCV (European Conference on Computer Vision), 2022.

paper code

IMLH 22

CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN

Matan Atad*, Vitalii Dmytrenko*, Yitong Li*, Xinyue Zhang*, Matthias Keicher, Jan Kirschke, Bene Wiestler, Ashkan Khakzar, Nassir Navab.

(* Equal Contribution)

IMLH (ICML 2022 Interpretable Machine Learning in Healthcare Workshop), 2022.

paper code

CVPR 22

PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects

Pengyuan Wang, HyunJun Jung, Yitong Li, Siyuan Shen, Rahul Parthasarathy Srikanth, Lorenzo Garattoni, Sven Meier, Nassir Navab, Benjamin Busam.

CVPR (IEEE/CVF Conference on Computer Vision and Pattern Recognition), 2022.

paper

ICRA 21

Two-stream 2D/3D Residual Networks for Learning Robot Manipulations from Human Demonstration Videos

Xin Xu, Kun Qian, Bo Zhou, Shenghao Chen, Yitong Li.

ICRA (IEEE International Conference on Robotics and Automation), 2021.

paper

Working Experience

Zillow Group Inc.

AI Applied Scientist, PhD Intern in Generative Computer Vision

Jun 2026 – Dec 2026

Munich, Germany

PreciTaste (PreciBake) GmbH

Working Student for Machine Learning Applications

Sep 2022 – Dec 2022

Munich, Germany

Chair of Computer Aided Medical Procedures, TUM

Research Assistant for 3D Computer Vision

Jun 2021 – Jun 2022

Munich, Germany

Department of Radiology, LMU Munich

Research Assistant for Medical Applications

Nov 2021 – Mar 2022

Munich, Germany

Institute of Automation, Chinese Academy of Sciences

Algorithm Engineer Intern

Jul 2020 – Nov 2020

Nanjing, China

Education

Apr 2023 – Dec 2026

Ph.D. Student

Technical University of Munich (TUM), School of Computation, Information and Technology

Oct 2020 – Mar 2023

M.Sc. Biomedical Computing

Technical University of Munich (TUM), School of Computation, Information and Technology

Aug 2016 – Jul 2020

B.Eng. Robot Engineering

Southeast University (SEU), School of Automation