Knowledge Distillation with Helen Byrne
Knowledge Distillation is the podcast that brings together a mixture of experts from across the Artificial Intelligence community.
We talk to the world’s leading researchers about their experiences developing cutting-edge models as well as the technologists taking AI tools out of the lab and turning them into commercial products and services.
Knowledge Distillation also takes a critical look at the impact of artificial intelligence on society – opting for expert analysis instead of hysterical headlines.
We are committed to featuring at least 50% female voices on the podcast – elevating the many brilliant women working in AI.
Host Helen Byrne is a VP at the British AI compute systems maker Graphcore where she leads the Solution Architects team, helping innovators build their AI solutions using Graphcore’s technology.
Helen previously led AI Field Engineering and worked in AI Research, tackling problems in distributed machine learning.
Before landing in Artificial Intelligence, Helen worked in FinTech, and as a secondary school teacher. Her background is in mathematics and she has a MSc in Artificial Intelligence.
Knowledge Distillation is produced by Iain Mackenzie.
Knowledge Distillation with Helen Byrne
Stable Diffusion 3 with Stability AI's Kate Hodesdon
Stability AI’s Stable Diffusion model is one of the best known and most widely used text-to-image systems.
The decision to open-source both the model weights and code has ensured its mass adoption, with the company claiming more than 330 million downloads.
Details of the latest version - Stable Diffusion 3 - were revealed in a paper, published by the company in March 2024.
In this episode, Stability AI’s Kate Hodesdon joins Helen to discuss some of SD3’s new features, including improved capabilities for generating text within images and overall image quality.
Kate also talks about developments to the underlying model structure of Stable Diffusion, as well as the challenges associated with creating models that deliver more efficient inference.
The Stable Diffusion 3 paper can be found here: https://arxiv.org/pdf/2403.03206.pdf