Jul 2, 2026 · 22 min · 9 segments
Send us Fan Mail Diffusion models have become the foundation of modern generative AI, powering state-of-the-art systems for image generation, video…
Aaron McClendonHost
So they point out that in the last few years, we've seen this kind of revolution in generative AI.
Obviously, things like ChatGBT and LLM-based transformer models have played a large role in that revolution.
However, there's another parallel track that's been developed recently um image image generation models like nano banana stable diffusion 3 stable diffusion which i guess is still a company i don't even remember i remember there's a news article last i heard the ceo was walking around in his underwear downtown but anyways they definitely released some pretty good open source models uh and um there was also the dali model which was a Hidden from the public architecture, I believe, but was presumably a diffusion model.
And there's also been interesting integrations between diffusion modeling and transformers.
There's a paper out of NVIDIA using diffusion model type things for token generation and selection.
and I guess sort of like the JEPA model is in the same vein of a diffusion model where you're sort of thinking in latent space sort of things VO3 video models so yeah a lot of stuff has been happening in that space and they branch and the goal of the lecture series is to talk through diffusion models and flow matching models.
And they all kind of started – I believe the original idea for a diffusion model was from someone who was a physicist studying Brownian motion, which is sort of like stochastic movement of molecules through a medium.
So if you think of starting out with a TV screen that's all fuzzy, just the black and gray dots, some people may not even remember when TVs did things like that before streaming services, but you hopefully know what I'm talking about.
And if you kind of wiggle the antenna on the TV you can eventually get a signal start to come through.
And maybe it's a little staticky at first, but the more you wiggle the antenna, the better the signal becomes and the clearer the picture is.
And that sort of iterative building of the picture from a noisy space is like what a diffusion model is doing.
And the evolution process, the guiding process from noise to data, is facilitated by simulating differential equations, ordinary or stochastic differential equations.
ordinary corresponds to flow models and the normal diffusion models correspond to the stochastic SDEs.
So they point out that in the last few years, we've seen this kind of revolution in generative AI.
Obviously, things like ChatGBT and LLM-based transformer models have played a large role in that revolution.
However, there's another parallel track that's been developed recently um image image generation models like nano banana stable diffusion 3 stable diffusion which i guess is still a company i don't even remember i remember there's a news article last i heard the ceo was walking around in his underwear downtown but anyways they definitely released some pretty good open source models uh and um there was also the dali model which was a Hidden from the public architecture, I believe, but was presumably a diffusion model.
And there's also been interesting integrations between diffusion modeling and transformers.
There's a paper out of NVIDIA using diffusion model type things for token generation and selection.
and I guess sort of like the JEPA model is in the same vein of a diffusion model where you're sort of thinking in latent space sort of things VO3 video models so yeah a lot of stuff has been happening in that space and they branch and the goal of the lecture series is to talk through diffusion models and flow matching models.
And they all kind of started – I believe the original idea for a diffusion model was from someone who was a physicist studying Brownian motion, which is sort of like stochastic movement of molecules through a medium.
So if you think of starting out with a TV screen that's all fuzzy, just the black and gray dots, some people may not even remember when TVs did things like that before streaming services, but you hopefully know what I'm talking about.
And if you kind of wiggle the antenna on the TV you can eventually get a signal start to come through.
And maybe it's a little staticky at first, but the more you wiggle the antenna, the better the signal becomes and the clearer the picture is.
And that sort of iterative building of the picture from a noisy space is like what a diffusion model is doing.
And the evolution process, the guiding process from noise to data, is facilitated by simulating differential equations, ordinary or stochastic differential equations.
ordinary corresponds to flow models and the normal diffusion models correspond to the stochastic SDEs.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
