Generative Modelling

Generative modeling aims to create new data instances resembling a given dataset, learning its underlying distribution. Current research heavily focuses on diffusion models and their variants, alongside refinements of generative adversarial networks (GANs), with applications spanning image generation, graph creation, and even scientific simulations like particle collision modeling. These advancements are impacting diverse fields, from improving medical image analysis and accelerating scientific computations to enhancing creative content generation and addressing challenges in federated learning environments.