🆕Building Generative Image & Video models at Scale https://t.co/cGGJVi5E1Y A lot of interest in i...
TL;DR · AI 摘要
Google DeepMind研究员Sander Dieleman分享生成式图像与视频模型的最新进展，涵盖建模、架构、蒸馏与控制技术。
核心要点
- 演讲覆盖生成模型从架构设计到控制信号的完整技术栈。
- 主讲人参与AlphaGo、Veo等项目，兼具理论与工程经验。
- 内容基于YouTube演讲视频，缺乏文字深度解析或代码实践。
https://t.co/Z09QkX7vuV
A lot of interest in image gen recently! @sedielem is here to give a concise State of the Art overview of Generative Image and Video models, from Modeling and Architecture to Distillation and Control https://t.co/gIjHHvGPW4" / X
AI Engineer on X: "🆕Building Generative Image & Video models at Scale https://t.co/Z09QkX7vuV A lot of interest in image gen recently! @sedielem is here to give a concise State of the Art overview of Generative Image and Video models, from Modeling and Architecture to Distillation and Control https://t.co/gIjHHvGPW4" / X
Don’t miss what’s happening
Building Generative Image & Video models at Scale https://youtube.com/watch?v=xOP1PM 8fwnk… A lot of interest in image gen recently!
is here to give a concise State of the Art overview of Generative Image and Video models, from Modeling and Architecture to Distillation and Control Signals!! From his Research Science post at
, his storied career from early AlphaGo to now leading research on Veo and
(and Gemini diffusion?), and one of the most beloved AI blogs in the world, we were honoured to host this special talk from Sander on home turf in London. Enjoy this special presentation!
Quote
Andrej Karpathy
@karpathy
·
Apr 5, 2023
Common Q: Can you train language model w diffusion? Favorite A: read this post (the whole blog is excellent) (Roughly speaking state of the art generative AI is either trained autoregressively or with diffusion. The underlying neural net usually a Transformer.) x.com/sedielem/statu…
·
2
4
16
13