Multimodal Generative AI Demystified

Explore the intricacies of multimodal generative AI in this 28-minute conference talk delivered by Ekaterina Sirazitdinova, Senior Data Scientist at Nvidia. Gain insights into the inner workings of these complex models, understanding key concepts and techniques used in their development. Discover various applications and use cases of multimodal generative AI, which enables the creation of realistic images, videos, and audio from textual or other inputs. Learn from Ekaterina's expertise in leveraging AI techniques for computer vision and language processing challenges, as well as her experience in end-to-end AI productization. Benefit from her background in medical image analysis and her academic achievements, including a Ph.D. in Computer Science and publications on image-based 3D reconstruction, localization, and tracking. Recorded at the 2024 GAIA Conference, this talk is suitable for anyone interested in the current state of AI and its potential to produce realistic and immersive multimedia experiences.