COSC 89.32 Multi-modalities Generative AI
This advanced course delves into the exciting field of Multi-modalities Generative AI, where students will explore the convergence of multiple data modalities such as text, image, and audio to create sophisticated and expressive AI models. This course is divided into two equally important components. The first half will consist of a lecture series that systematically covers fundamental concepts and technologies in generative AI. This segment aims to establish a solid theoretical foundation while facilitating hands-on learning through practical demonstrations with open-source examples. The second half of the course will be an interactive reading group, where students delve into influential papers and engage in in-depth discussions. This segment is designed to foster critical thinking, encourage exploration of the latest research in multi-modal generative AI.
Students will undertake a term project directly related to Multi-modalities Generative AI. This project will provide an opportunity to apply the acquired knowledge and skills, fostering creativity and innovation in the development of multi-modal generative models. By combining a lecture series, engaging reading group discussions, and a practical term project, this course aims to equip students with a well-rounded understanding of multi-modal generative AI and the ability to contribute meaningfully to this rapidly evolving field.
Department-Specific Course Categories
Computer Science