Generative AI is at the peak of the Gartner Hype Cycle, with applications spanning text, image, audio, and video generation.
Large language models (LLMs) function as next-word predictors, generating text token by token in a process that creates a typewriter-like effect.
Text is broken down into numerical tokens and then mapped into a multi-dimensional vector space where semantically similar words are located close together.
The transformer architecture uses an attention mechanism to weigh the importance of different words in the input sequence to understand context and resolve ambiguity.
The CLIP model establishes a shared embedding space for text and images, enabling the system to measure the semantic similarity between a text description and a picture.
Diffusion models generate images through an iterative process of predicting and subtracting noise from a random starting point, guided by a text prompt's embedding.
Video generation uses a diffusion transformer to maintain coherence across frames by processing video in patches and applying the denoising process to the entire sequence.
Beyond simple generation, models can perform image-to-video conversion, extend existing clips, interpolate between two different videos, or edit specific regions.
Generative video models still struggle with understanding cause and effect, leading to physically impossible events and objects appearing or behaving illogically.
Major ethical concerns include the use of copyrighted or publicly available data without consent for training models, leading to legal challenges and questions about ownership.
msg
Ismaning, Germany
29:27David Estevez
56:55Ekaterina Sirazitdinova
25:17Scott Hanselman
30:38Timo Zander
27:12Damir
25:14Jonas Andrulis
24:51Simon Müller
28:30Cheuk Ho
Jobs that call for the skills explored in this talk.
Collaboration Betters The World GmbH
ADS LLC /
Denver, United States of America
Amazon.com, Inc
München, Germany
