Chenyu You – Research
Full publications on Google Scholar. Research Summary: My research interest is in Biomedical AI. Specifically, I works to develop the principles and practice of generalizable, robust, and trustworthy machine learning for healthcare. Some recent highlights include (i) robust machine learning for imperfect medical data, (ii) multi-modal biomedical data analytics, and (iii) natural language processing (NLP) in healthcare. ‡ indicates authors with equal contribution. ☆ indicates authors working closely with me. (Robust) Machine Learning for Imperfect Medical DataThe development of machine learning models, particularly in the context of label scarcity, increasingly necessitates the collection of substantial annotated medical data. Moreover, medical data often display a long-tailed class distribution, which consequently results in notable imbalance issues. To this end, there are several growing interests in training machine learning models jointly across imbalanced class distributions and limited annotations. I have developed novel, efficient, statistically consistent algorithms to improve empirical performance for biomedical image analysis.
Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation Learning with Theoretical GuaranteesAs machine learning methods have become ubiquitous in clinical decision-making, their reliability and interpretability have become important. This is particularly crucial in the field of biomedical image analysis, where decision outcomes can have profound implications. I have developed novel machine learning algorithms that enable provably accurate anatomical modeling with theoretical guarantees. Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective Foundation Models for Biomedical DataThe development of medical foundation models often requires massive and diverse biomedical data. To this end, I have developed various foundation models for biomedical imaging data and explored novel applications of these models. I have also developed novel medical AI Agents that lead to the scalable and accurate predictive modeling, particularly for distribution shift problems. Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts Multi-Modal Biomedical Data AnalyticsReal-world machine learning often requires multi-modality biomedical data for disease prevention, diagnosis, prognosis, and treatment design. I have developed multi-modality learning algorithms (e.g., multimodal foundation model), primarily through the use of foundation models and probabilistic graphical analyses. These tools are principally employed to facilitate clinical research. I have also developed novel methods that effectively tackle clinical challenges associated with data heterogeneity.
End-to-end Spoken Conversational Question Answering: Task, Dataset and Model Funding: I graciously acknowledge generous funding support from the National Institutes of Health, National Science Foundation, and the Yale Fellowships and Funding. My research is also supported by generous computing support from Yale Center for Research Computing, Meta AI, Google Cloud, and Amazon Web Services. |