Sander Dieleman
where else to find them
website:https://sander.ai/
github:benanne
bluesky:sedielem.bsky.social
x:sedielem
linkedin:sanderdieleman
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Chris Donahueonce
- Ian Simononce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Building Generative Image & Video models at Scale | AI Engineer Europe 2026 | 2026-04-08 |
Shows that large-scale image and video generation trains diffusion models on latent autoencoders (EQ‑VAE / Stable Diffusion style) to cut tensor size by ~100x… | ||
| Piano Genie | IUI 2019 | 2019-03-17 |
Piano Genie maps an 88-key piano to an eight-button controller by training a recurrent neural network autoencoder with a discrete bottleneck: an encoder learns… | ||
| nothing matches | ||