Skip to content
Technical University of Munich

Generative Multimedia

Lecturer (assistant)
Rahul Chaudhari
Zongxie Chen
Number 0000003006
Type lecture with integrated exercises
Duration 4 SWS
Term Winter semester 2026/27
Language of instruction English
Position within curricula See TUMonline
Dates See TUMonline

Admission information

See TUMonline

Description

- Introduction to probability theory, generative modeling, and Deep Learning
- Maximum Likelihood Learning and Sampling techniques
- Theory and applications of Autoregressive models, Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Energy-based models and normalizing flows, Transformers, Diffusion models, Multimodal models (language-image), etc.
- Creative applications: image synthesis, text-to-image generation, and music composition
- Tiny Generative Models for Edge Devices (challenges and techniques for running generative models on resource-constrained hardware, model compression, quantization, and software frameworks

Prerequisites

Probability theory, Linear Algebra, Optimization

Teaching and learning methods

Lectures introduce theoretical concepts, providing context, and discussing real-world applications. Tutorial sessions consist of hands-on implementation, where students apply theoretical knowledge to coding assignments. Tutorial sessions may also include derivations that could not be covered in depth during the lecture.

Teaching methods
- Presentation slides with theory, applications, and discussions on research papers
- Interactive coding sessions
- Guest lectures from industry experts (if available)

Learning methods
- Tutorials with programming assignments to build and train generative models
- Essays summarizing and critiquing cutting-edge research papers

Links

To top