My main research interest is Synthetic Data Generation and its application in various Vision/Text tasks. Specifically my current approach is to study if it is possible to use the Generative Models like StyleGANs, Diffusion and Flows to further enhance the Discriminative models (e.g., Classifiers). Conceptually this have some common grounds with Analysis by Synthesis idea. In essence it it addressing fundamental synergy of Discriminative and Generative modeling.