BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Imaging Seminar: Generative AI\, Stable Diffusion\, and the Revolu
 tion in Visual Synthesis Abstract
DTSTART:20230316T170000
DTEND:20230316T180000
DTSTAMP:20260406T210748Z
UID:d636c2bfe29cf4262402ab12a97456924a9d477e7ae5612f703176e3
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Björn Ommer\, Ludwig Maximilian University of Munich\n
 Abstract:\nRecently\, deep generative modeling has become the most promine
 nt paradigm for learning powerful representations of our (visual) world an
 d for generating novel samples thereof. Consequently\, this has already be
 come the main building block for numerous algorithms and practical applica
 tions. This talk will contrast the most commonly used generative models to
  date with a particular focus on denoising diffusion probabilistic models\
 , the core of the currently leading approaches to visual synthesis. Despit
 e their enormous potential\, these models come with their own specific lim
 itations. We will then discuss a solution\, latent diffusion models a.k.a.
  “Stable Diffusion”\, that significantly improves the efficiency of di
 ffusion models. Now billions of training samples can be summarized in comp
 act representations of just a few gigabyte so that the approach runs on co
 nsumer hardware. Making high-quality visual synthesis accessible to everyo
 ne has revolutionized the way we create visual content and spurred researc
 h and the development of numerous novel applications.\nWe will then discus
 s recent extensions that cast an interesting perspective on future generat
 ive modelling. Time permitting\, the talk will also cover applications of 
 generative AI in the life sciences and beyond.\n\nBiography:\nBjörn Ommer
  is a full professor at the University of Munich where he is heading the C
 omputer Vision and Learning Group. Before he was a full professor in the d
 epartment of mathematics and computer science at Heidelberg University and
  a co-director of the IWR and the HCI. He received his diploma in computer
  science from University of Bonn and his PhD from ETH Zurich. Thereafter\,
  he was a postdoc in the vision group of Jitendra Malik at UC Berkeley.Bj
 örn serves as an associate editor for IEEE T-PAMI. His research interests
  include semantic scene understanding and retrieval\, generative AI and vi
 sual synthesis\, self-supervised metric and representation learning\, and 
 explainable AI. Moreover\, he is applying this basic research in interdisc
 iplinary projects within the digital humanities and the life sciences. His
  group has published a series of generative approaches\, including “VQGA
 N” and “Stable Diffusion”\, which are now democratizing the creation
  of visual content and have already opened up a breadth of new directions 
 in research\, industry\, the media\, and beyond.\n\nThe talk is followed b
 y an aperitif. \nRegistration appreciated\nMore info here
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR