BITESIZE How Do Diffusion Models Work?

Today's clip is from Episode 151 of the podcast, with Jonas Arruda In this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure. Get the full discussion here • Join this channel to get access to perks: • Intro to Bayes Course (first 2 lessons free): • Advanced Regression Course (first 2 lessons free): Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at !

You can listen to BITESIZE How Do Diffusion Models Work? online on Radio and Podcast. Open the player on this page to stream the available audio.

BITESIZE How Do Diffusion Models Work? is an episode from Learning Bayesian Statistics by Alexandre ANDORRA.

This episode is 00:03:40 long.

This episode was published on Feb 19, 2026.

Yes. Use the heart button on the episode page to add it to your favorite episodes list.

Yes. This page shows related episodes from Learning Bayesian Statistics when more episodes are available from the podcast feed.