Generative AI - An intro to flow matching (FM) and diffusion models

AGENDA
We'll walk through the theory and practice of nowadays' state of the art models in dense data structure generation (image / video / proteins....) .In this meetup series we had quite a lot of sessions about LLM-based models focusing on next token prediction. Now we move to a very different model family.We'll give an intro to the mathematical background of flow matching and diffusion models. This will give us a chance to understand the common parts of their origins - simulating ordinary & stochastic differential equations. And also, it'll shed light on the difference between the 2 model classes.After the math intro we'll formulate the training objective and closely observe the architecture of a flow-based image generation model.

ENTRY DETAILS
Please look for and download the QR code attached this event page. The code will appear by the week of the event. The gates are quirky, so please increase your phone's screen brightness to maximum and hold it at a 5-10 cm distance from the scanner to help it focus. Please hold onto the codes as you will need them both in and out!

We will be waiting for you in the lobby to help.

PAST EVENTS
Materials from past events are listed here:
https://www.turbine.ai/ai-meetup-presentations