👨‍🎓 I’m Jiyao Liu (刘继垚), currently a third-year Ph.D. student at Institute of Science and Technology for Brain-Inspired Intelligence (ISTBI), Fudan University. I am honored to be advised by Prof. Ningsheng Xu. Previously, I received the Bachelor’s degree (June 2022) in Intelligence Science and Technology from Xidian University.

🔭 Research interests

My research focuses on artificial intelligence, with particular emphasis on general medical AI, inverse problem in medical imaging, multi-modal large language models, as well as other new AI technologies. Feel free to reach out if you’d like to learn more about my work, chat, or explore potential collaborations.

🔥 News

2025.05: 🎉🎉 Two paper has been early accepted by MICCAI.
2024.11: 🎉🎉 I start my new journey at Shanghai AI Lab.
2023.10: 🎉🎉 One paper has been oral reported on SASHIMI, MICCAI workshop, 2023.
2021.12: I started my research on Cross-modality face recognition with Dr. Qigong Sun from SenseTime Group.
2021.05: 🎉🎉 MCM/ICM, Mathematical Contest in Modeling, Outstanding Winner🎉（美国大学生数学建模竞赛特等奖，O奖）

📝 Publications

sensitivity1.png

Submited to IEEE TMI

A New Framework of Implicit Prior Adaptation for Boosting Test-Time MRI Reconstruction

Jiyao Liu, Shangqi Gao, Xiao-Yong Zhang, Ningsheng Xu and Xiahai Zhuang

In this work, we propose a zero-shot adaptation framework tailored to the reference phase of an implicit prior-based MRI reconstruction model. This framework is designed to seamlessly integrate with any contemporary implicit prior-based methods without modifying their architectures or pre-trained weights. Our approach requires only the automatic adjustment of three scaling factors during inference.

MICCAI 2025

Multi-modal MRI Translation via Evidential Regression and Distribution Calibration

Jiyao Liu, Shangqi Gao, Yuxin Li, Lihao Liu, Xin Gao, Zhaohu Xing, Junzhi Ning, Yanzhou Su, Xiao-Yong Zhang, Junjun He, Ningsheng Xu, Xiahai Zhuang

We propose a novel framework for multi-modal MRI translation that tackles two key challenges: lack of uncertainty quantification and poor cross-center robustness. By framing the task as evidential regression with distribution calibration, our method fuses multi-source information with uncertainty modeling and adapts to domain shifts. Experiments on BraTS2023 datasets show improved performance and generalization.

MICCAI workshop 2023 oral

Multi-Phase Liver-Specific DCE-MRI Translation via a Registration-Guided GAN

Jiyao Liu, Yuxin Li, Nannan Shi, Yuncheng Zhou, Shangqi Gao, Yuxin Shi , Xiao-Yong Zhang, Xiahai Zhuang

Project

This paper introduces a new dataset and a novel application of image translation from multi-phase DCE-MRIs into a virtual GED- HBP image (v-HBP) that could be used as a substitute for GED-HBP in clinical liver diagnosis.

🎖 Honors and Awards

2022.06 Undergraduate Excellence Award.
2021.05 MCM/ICM, Mathematical Contest in Modeling, Outstanding Winner | [blog] | [github].
2019/2020/2021 National Endeavor Scholarship (BSc), Xidian University.
📖 Educations
2022.09 - 2027.06 (now), P.h.d., Fudan University, Shanghai.
2018.09 - 2022.06, B.S., Xi Dian University, Xi’an.