Liyue Shen is an assistant professor in the ECE Division of the Electrical Engineering and Computer Science Department of the College of Engineering, University of Michigan – Ann Arbor. She is also affiliated with Michigan Institute for Data Science (MIDAS), Michigan Institute for Computational Discovery and Engineering (MICDE) and Michigan Materials Research Institute (MMRI).
She received her B.E. degree in Electronic Engineering from Tsinghua University in 2016, and obtained her Ph.D. degree from the Department of Electrical Engineering, Stanford University in 2022, co-advised by Prof. John Pauly and Prof. Lei Xing. She was a postdoctoral research fellow at the Department of Biomedical Informatics, Harvard Medical School from 2022 to 2023. She is the recipient of Stanford Bio-X Bowes Graduate Student Fellowship (2019-2022), and was selected as the Rising Star in EECS by MIT and the Rising Star in Data Science by The University of Chicago in 2021.
Her research interest is in Biomedical AI, which lies in the interdisciplinary areas of machine learning, computer vision, signal and image processing, medical image analysis, biomedical imaging, and data science. She is particularly interested in developing efficient and reliable AI/ML-driven computational methods for biomedical imaging and informatics to tackle real-world biomedicine and healthcare problems, including but not limited to, personalized cancer treatment, and precision medicine. She recently focuses on the generative diffusion models, implicit neural representation learning and multimodal foundation models.
She co-organized the Woman in Machine Learning (WiML) workshop at ICML’ 21, and the Machine Learning for Healthcare (ML4H) workshop at NeurIPS’ 21. In MICCAI’ 21, she co-taught the tutorial on Deep 2D-3D Modeling and Learning in Medical Image Computing.
News
- Invited to give a talk at the Tools and Technology Seminar for the Department of Computational Medicine and Bioinformatics at the University of Michigan (Feb. 2025)
- Invited to give a talk at the 2025 Statistics Annual Winter Workshop at the University of Florida (Jan. 2025)
- Invited to give a talk at online Monte Carlo Seminar (Nov. 2024)
- Invited to give a guest lecture at AI in BME class (BME 487) at University of Michigan (Nov. 2024)
- Our paper TempA-VLP: Temporal-Aware Vision-Language Pretraining for Longitudinal Exploration in Chest X-ray Image has been accepted by WACV’25. (Oct. 2025)
- Invited to serve as the Associate Editor for the journal Medical Physics. (Oct. 2024)
- Two papers DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction and Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems have been accepted by NeurIPS’24. (Sep. 2024)
- We organize a research symposium together with U-M MIDAS and ECE: Generative AI: From Theory to Scientific Applications. (Sep. 2024)
- Our paper Accelerated Wirtinger Flow with Score-based Image Priors for Holographic Phase Retrieval in Poisson-Gaussian Noise Conditions has been accepted by IEEE Transactions on Computational Imaging. (Sep. 2024)
- Release our new paper on arXiv: Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing. (Aug. 2024)
- Invited to serve as the Area Chair for the conference ICLR’25. (Aug. 2024)
- Taught a U-M ECE Summer Tech Camp for high school students: “AI Magic Program“. (Aug. 12-16th, 2024)
- Our paper Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems was presented at Computational Imaging Workshop hosted by The Institute for Mathematical and Statistical Innovation (IMSI). (Aug. 2024)
- Invited to give a talk about Fundamentals and Applications of Implicit Neural Representation Learning at 2024 American Association of Physicists in Medicine (AAPM) Annual Meeting. (Jul. 2024)
- Invited to serve on the organization committee of the 2nd Conference on Parsimony and Learning (CPAL) as a Rising Stars Award Chair. (Jul. 2024)
- Our paper CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems has been accepted by ECCV’24. (Jul. 2024)
- Our paper Efficient In-Context Medical Segmentation with Meta-driven Visual Prompt Selection has been accepted by MICCAI’24. (Jun. 2024)
- Our papers DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction and SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models have been accepted to present at ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling. (Jun. 2024)
- Our paper The Emergence of Reproducibility and Consistency in Diffusion Models has been accepted by ICML’24. (May. 2024)
- Our paper Missing Wedge Completion via Unsupervised Learning with Coordinate Networks has been accepted by International Journal of Molecular Sciences. (Apr. 2024)
- ECE PhD student, Jason Hu, is recognized as Honorable Mention for NSF Graduate Research Fellowship Program (GRFP) 2024. (Apr. 2024)
- Invited to serve on the organization committee of ISBI 2025 Meeting (Student and Young Professional Activity Chair). (Apr. 2024)
- Invited to give a talk about Biomedical AI in the Seminar of University of Michigan’s Department of Computational Medicine & Bioinformatics. (Apr. 2024)
- Release our new paper on arXiv: Align as Ideal: Cross-Modal Alignment Binding for Federated Medical Vision-Language Pre-training. (Apr. 2024)
- Invited to give a talk about Medical AI in the research meeting of Harvard Medical School. (Apr. 2024)
- Incoming ECE PhD student, Lixuan Chen, is awarded a 2024-2025 MICDE Fellowship by University of Michigan. (Mar. 2024)
- Release our new paper on arXiv: Part-aware Personalized Segment Anything Model for Patient-Specific Segmentation. (Mar. 2024)
- Invited to give a talk about AI for Medical and Scientific Applications at MICDE AI and Computational Science for Astronomy/Astrophysics workshop, and Environmental Statistics Symposium on Artificial Intelligence and Environmental Health Sciences. (Mar. 2024)
- Invited to give a talk about AI for Medical Imaging at University of Michigan’s Department of Radiology. (Feb. 2024)
- Invited to serve as the Area Chair for the conference of Machine Learning for Healthcare MLHC’24. (Feb. 2024)
- Invited to give a guest lecture about Medical AI in the course of CSCI 699 at University of Southern California, and CSE 290D at University of California, Santa Cruz. (Jan 2024)
- Our paper Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency has been accepted by ICLR’24 as a Spotlight (top 5%). (Jan. 2024)
- Invited to serve as the Area Chair for the conference ICLR’24. (Dec. 2023)
- Our paper The Emergence of Reproducibility and Consistency in Diffusion Models, has been awarded as the Best Paper Award at NeurIPS Diffusion Model Workshop 2023. (Nov. 2023)
- Elected to serve on the IEEE Computational Imaging Technical Committee (CI TC) for a 3-year term starting January 2024. (Nov. 2023)
- Invited to give a talk at UMich Department of Learning Health Sciences (DLHS) Research Seminar about AI for Medical Imaging. (Nov. 2023)
- Received a grant of 2023 MICDE Catalyst Grant from Michigan Institute for Computational Discovery and Engineering (MICDE) in collaboration with Prof. Qing Qu and Prof. Jeffrey A. Fessler, for supporting our research on Efficient Diffusion Models for Scientific Machine Learning. (Oct. 2023)
- Invited to serve as the Associate Editor for the journal BJR|Artificial Intelligence. (Oct. 2023)
- Release our new paper on arXiv: The Emergence of Reproducibility and Consistency in Diffusion Models. Short version is selected as an oral (top 2%) at NeurIPS 2023 Workshop on Diffusion Models. (Oct. 2023)
- Release our new paper on arXiv: Poisson-Gaussian Holographic Phase Retrieval with Score-based Image Prior. Short version is accepted at NeurIPS 2023 Deep Learning and Inverse Problems Workshop. (Sep. 2023)
- Invited to give talks at ICCV 2023 Computer Vision for Automated Medical Diagnosis (CVAMD) Workshop, UMich MIDAS mini-symposium on AI for Medical Imaging, UMich ECE Communications and Signal Processing Seminar about our recent work using latent diffusion models for solving general inverse problems. Please check the video recording. (Sep. 2023)
- Organize research symposium at U-M MIDAS: Generative AI: Diffusion Models for Scientific Machine Learning. (Sep. 2023)
- Release our new paper on arXiv: Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency. (Jul. 2023)
- Received a grant of Propelling Original Data Science (PODS) 2023 award from Michigan Institute for Data Science (MIDAS) in collaboration with Prof. Lise Wei (UMich Medicine), for supporting our collaborative research on personalized progression risk prediction for cancer patients from longitudinal multi-modality data. (Jun. 2023)
- Organization committee for a new conference: Conference on Parsimony and Learning (CPAL), which will be held in Jan. 2024.