Head of research
Youssef is a machine learning scientist with a passion for computer vision. He enjoys learning new theoretical aspects and finding useful applications for generative models.
Talk, listen, see: the three levels of interactive video agents
Interactive Avatar Models are video generation models focused on producing a talking video of an agent reacting to a human in the context of a conversation, at latencies low enough to support real dialogue.
Try Synthesia with a free video.
Type a prompt and add context. Get a finished video in minutes. No credit card required.