Seminar Generative AI

Generative artificial intelligence is ubiquitous in our daily life, generating synthetic images, text, sound tracks, and videos. Example tasks include image synthesis, image styling, text to image synthesizing, voice to text translation, text translation, and question and answering.

The aim of this seminar course is to let students learn the principles and models of generative AI via paper reading, presentation, and discussion. We provide a broad overview on the design of the state-of-the-art generative models, spanning from generative adversarial networks, diffusion models and generative pre-trained transformers (GPT). We will present an array of methodologies and techniques that can efficiently and effectively train generative models against all operational conditions.

The course materials will be based on a mixture of classic and recently published papers. The first 4 lectures, the basic concept of distributed machine learning will be covered, followed by presentations from my PhD students and the students taking this course.


Code 12574
Type Seminar
Site Neuchâtel
Track(s) T1 – Distributed Software Systems
T6 – Data Science
Semester S2024


Learning Outcomes
  • To understand and analyze the basic deep generative models, i.e., autoencoder, generative adversarial networks, diffusion models, and GPT.
  • To understand how to train the deep generative models in a centralized and decentralized way
  • To understand how generative models applied on different data types, e.g., images, tables, and time series.
  • To analyze the performance and computational tradeoff among different generative models
  • To understand the use cases of generative models and apply them
Lecturer(s) Lydia Chen
Language english
Course Page

The course page in ILIAS can be found at

Schedules and Rooms

Period Weekly
Schedule Monday, 14:15 - 16:00
Location UniNE, Unimail
Room B217


Evaluation type continuous evaluation

Additional information


First Lecture
The first lecture will take place on Monday, 19.02.2024 at 14:15 in UniNE, Unimail, room B217.