Recent Advances in Generative Modeling and Synthetic Biomedical Data

The growing use of electronic health records (EHRs) and biomedical data presents new opportunities and challenges for developing generative models that can produce
realistic synthetic data while safeguarding privacy and reducing bias. In this talk, I will present recent advances in generative modeling for biomedical data, including
diffusion-based methods for privacy-preserving EHR time series, a new semi-parametric copula flow approach for irregularly sampled functional data, and a
bias-corrected synthesis framework that improves learning in imbalanced rare-event
settings. These techniques together form a toolkit for generating reliable, privacy-conscious synthetic data and expanding the usability of sensitive biomedical datasets.