What we’re about
MEETUPS ARE TO BE HELD ON THE LAST WEDNESDAY OF EVERY MONTH IN 2024
Turbine's AI meetups are meant for all researchers, engineers, scientists and students working on hard machine learning problems. It is created to dissect and understand new developments in ML together, and share our experience from real-life projects.
Presenters cover the latest impactful AI models, aiming to dive much deeper into each topic than what standard science communication formats allow. Thus, they'll expect you to have a working knowledge of machine learning.
In some sessions, we are going deep to understand recently published models and architectures - with working code whenever possible & intro to math background whenever needed. In others, presenters share their learnings working on models of real-life applications. Our goal is to give thorough knowledge to the audience, that you will use in model design on a daily basis.
Turbine is a computational biology company focusing on cancer, so expect lots of topics infused with biology. Yet, we are also a curious community, inviting you to join even if your personal interest centers around other domains. We also host completely biology-free events about computer vision, NLP and generic AI topics to cover the latest scientific advancements.
Select past presentations can be found here:
https://www.turbine.ai/ai-meetup-presentations
Upcoming events (1)
See all- Generative AI (cont.) - Diffusion Transformer models (DiT)Turbine Kft., Budapest
AGENDA
This month's session is about Diffusion Transformer models (DiT).Last time we built up the math framework of flow and diffusion models and used a U-Net inside it as a concrete implementation to generate images. This time we'll check if we can use transformers instead of the U-Net with convolutions. To understand the benefits of transformers over convolution in generative AI, we'll first discuss differences between pixel vs. latent space diffusion through an image generation example.
We'll start using transformers from the base architecture of vision transformer (ViT) models and walk through our way to the topic of how to apply them in a diffusion setting instead of the usual autoregressive setups.
Finally, we'll give a quick peek into multi-modal image generation - where we condition our model with complex textual prompts instead of a class label only.The session will discuss the content mostly of the following papers: Scalable Diffusion Models with Transformers --- https://arxiv.org/pdf/2212.09748 Scaling Rectified Flow Transformers for High-Resolution Image Synthesis --- https://arxiv.org/pdf/2403.03206 High-Resolution Image Synthesis with Latent Diffusion Models --- https://arxiv.org/pdf/2112.10752
+1 thing: Watch out for the opening announcement of our Slack channel where you'll soon be able to recommend or vote future papers & topics. Details will be available on the meetup series' page: https://www.meetup.com/turbine-ai-meetups/
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
