# STEAM Academy Seminar: Diffusion Models for Image and Video Generation

- Institution: CERN
- Speaker: Sander Dr Dieleman
- Year: 2026
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3026732)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Abstract:

An intuitive perspective on the generative modelling paradigm that drives modern image and video generation.

Speaker's Bio:

Sander Dieleman is a Research Scientist at Google DeepMind in London, UK, where he has worked on the development of AlphaGo, WaveNet, Nano Banana, Gemini Omni, and more. He obtained his PhD from Ghent University in 2016. His current research interests include representation learning and generative modelling of audio, images and video.

This seminar is part of the CERN STEAM Academy Seminar Series.

Networking cocktail will follow the seminar.

A public webcast will be available and accessible to external participants.

With the support of CERN's Next Generation Triggers Project.

00:00:00 Slide 1

00:01:03 Slide 2

00:06:39 Slide 3

00:06:55 Slide 4

00:07:19 Slide 5

00:08:06 Slide 6

00:08:24 Slide 7

00:09:01 Slide 8

00:09:30 Slide 9

00:09:42 Slide 10

00:10:36 Slide 11

00:11:51 Slide 12

00:12:30 Slide 13

00:13:06 Slide 14

00:13:16 Slide 15

00:14:51 Slide 16

00:16:46 Slide 17

00:17:07 Slide 18

00:20:28 Slide 19

00:22:17 Slide 20

00:27:13 Slide 21

00:27:28 Slide 22

00:28:57 Slide 23

00:29:09 Slide 24

00:29:45 Slide 25

00:30:16 Slide 26

00:31:28 Slide 27

00:33:33 Slide 28

00:35:18 Slide 29

00:36:29 Slide 30

00:39:21 Slide 31

00:40:38 Slide 32

00:42:24 Slide 33

00:42:54 Slide 34

00:43:21 Slide 35

00:43:34 Slide 36

00:46:19 Slide 37

00:48:59 Slide 38

00:49:47 Slide 39

00:50:46 Slide 40

00:50:59 Slide 41

00:52:47 Slide 42

00:53:03 Slide 43

00:54:07 Slide 44

00:54:26 Slide 45

00:56:34 Slide 46

00:58:02 Slide 47

00:59:11 Slide 48

01:00:19 Slide 49

01:00:34 Slide 50

01:01:39 Slide 51

01:02:36 Slide 52

01:03:03 Slide 53

01:03:17 Slide 54

01:03:53 Slide 55

01:04:15 Slide 56

01:05:45 Slide 57

01:05:59 Slide 58

01:06:23 Slide 59

01:07:18 Slide 60

01:07:55 Slide 61

01:08:44 Slide 62

01:08:59 Slide 63

01:10:40 Slide 64

01:11:18 Slide 65

01:11:29 Slide 66

01:12:06 Slide 67

01:12:35…

## Lectures

1. [STEAM Academy Seminar: Diffusion Models for Image and Video Generation](https://invisiblenetwork.ai/learn/cern/3026732/488637806b46), 1 h 27 min (CERN's player)