Deep Generative Models (CS236)

This advanced course covers the theoretical foundations and practical applications of deep generative models. Students will learn to implement and evaluate state-of-the-art architectures such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), autoregressive models, flow-based models, diffusion models, and score-based generative models. The curriculum explores applications in computer vision, natural language processing, and audio synthesis, equipping participants with the skills to generate realistic data and understand recent research trends. Designed for graduate students and advanced undergraduates seeking expertise in cutting-edge generative AI.