Multimodal Generative AI Demystified
Offered By: Data Science Festival via YouTube
Course Description
Overview
Explore the intricacies of multimodal generative AI in this 41-minute talk by Ekaterina Sirazitdinova from NVIDIA, presented at the Data Science Festival. Delve into the key concepts and techniques behind these complex models that create realistic images, videos, and audio from textual or other inputs. Gain insights into the practical applications and use cases of this cutting-edge technology. Designed for technical practitioners and anyone interested in the current state of AI, learn how these models function and their potential to produce immersive multimedia experiences. This session, part of the Data Science Festival MayDay event 2024, offers a comprehensive look at the advancements in multimodal generative AI and its impact on creating realistic and engaging content.
Syllabus
Multimodal Generative AI Demystified - Data Science Festival
Taught by
Data Science Festival
Related Courses
AudioGen- Textually Guided Audio Generation - Paper ExplainedAleksa Gordić - The AI Epiphany via YouTube MusicLM Generates Music From Text - Paper Breakdown
Valerio Velardo - The Sound of AI via YouTube A Composer's Guide to Creating with Generative Neural Networks
GOTO Conferences via YouTube 21 Recent AI Updates in 23 Minutes
1littlecoder via YouTube Popcorn & Clocks - A Story About Scheduling in the Browser
NDC Conferences via YouTube