Lightnews — Scholar-powered news

Sander Dieleman

@sedielem.bsky.social

4.4K followers 620 following 89 posts

Blog: https://sander.ai/ 🐦: https://x.com/sedielem Research Scientist at Google DeepMind (WaveNet, Imagen 3, Veo, ...). I tweet about deep learning (research + software), music, generative models (personal account).

sander.ai

Posts Media Videos Starter Packs

Pinned

Sander Dieleman @sedielem.bsky.social · Apr 15

New blog post: let's talk about latents!
sander.ai/2025/04/15/l...

Generative modelling in latent space

Latent representations for generative models.

sander.ai

3 18 74

Sander Dieleman @sedielem.bsky.social · Jul 28

Great blog post on rotary position embeddings (RoPE) in more than one dimension, with interactive visualisations, a bunch of experimental results, and code!

On N-dimensional Rotary Positional Embeddings

An exploration of N-dimensional rotary positional embeddings (RoPE) for vision transformers.

jerryxio.ng

2 18

Sander Dieleman @sedielem.bsky.social · Jul 26

... also very honoured and grateful to see my blog linked in the video description! 🥹🙏🙇

Sander Dieleman @sedielem.bsky.social · Jul 26

I blog and give talks to help build people's intuition for diffusion models. YouTubers like @3blue1brown.com and Welch Labs have been a huge inspiration: their ability to make complex ideas in maths and physics approachable is unmatched. Really great to see them tackle this topic!

Grant Sanderson @3blue1brown.com · Jul 25

New video on the details of diffusion models: youtu.be/iv-5mZ_9CPY

Produced by Welch Labs, this is the first in a short series of 3b1b this summer. I enjoyed providing editorial feedback throughout the last several months, and couldn't be happier with the result.

But how do AI videos actually work? | Guest video by @WelchLabsVideo

YouTube video by 3Blue1Brown

youtu.be

1 30

Sander Dieleman @sedielem.bsky.social · Jul 15

Everyone is welcome!

Sander Dieleman @sedielem.bsky.social · Jul 15

Hello #ICML2025👋, anyone up for a diffusion circle? We'll just sit down somewhere and talk shop.

🕒Join us at 3PM on Thursday July 17. We'll meet here (see photo, near the west building's west entrance), and venture out from there to find a good spot to sit. Tell your friends!

1 13

Sander Dieleman @sedielem.bsky.social · Jul 5

Diffusion models have analytical solutions, but they involve sums over the entire training set, and they don't generalise at all. They are mainly useful to help us understand how practical diffusion models generalise.

Nice blog + code by Raymond Fan: rfangit.github.io/blog/2025/op...

2 3 33

Sander Dieleman @sedielem.bsky.social · Jun 24

Note also that getting this number slightly wrong isn't that big a deal. Even if you make it 100k instead of 10k, it's not going to change the granularity of the high frequencies that much because of the logarithmic frequency spacing.

Sander Dieleman @sedielem.bsky.social · Jun 24

The frequencies are log-spaced, so historically, 10k was plenty to ensure that all positions can be uniquely distinguished. Nowadays of course sequences can be quite a bit longer.

1 1

Sander Dieleman @sedielem.bsky.social · May 14

Here's the third and final part of Slater Stich's "History of diffusion" interview series!

The other two interviewees' research played a pivotal role in the rise of diffusion models, whereas I just like to yap about them 😬 this was a wonderful opportunity to do exactly that!

History of Diffusion - Sander Dieleman

YouTube video by Bain Capital Ventures

www.youtube.com

7 21

Sander Dieleman @sedielem.bsky.social · May 14

The ML for audio 🗣️🎵🔊 workshop is back at ICML 2025 in Vancouver! It will take place on Saturday, July 19. Featuring invited talks from Dan Ellis, Albert Gu, James Betker, Laura Laurenti and Pratyusha Sharma.

Submission deadline: May 23 (Friday next week)
mlforaudioworkshop.github.io

[“Machine Learning for Audio Workshop”]

[“Discover the harmony of AI and sound.”]

mlforaudioworkshop.github.io

1 12

Reposted by Sander Dieleman

Luca Ambrogioni @lucamb.bsky.social · Apr 29

I am very happy to share our latest work on the information theory of generative diffusion:

"Entropic Time Schedulers for Generative Diffusion Models"

We find that the conditional entropy offers a natural data-dependent notion of time during generation

Link: arxiv.org/abs/2504.13612

2 5 25

Sander Dieleman @sedielem.bsky.social · Apr 25

One weird trick for better diffusion models: concatenate some DINOv2 features to your latent channels!

Combining latents with PCA components extracted from DINOv2 features yields faster training and better samples. Also enables a new guidance strategy. Simple and effective!

Thodoris Kouzelis @nicolabourbaki.bsky.social · Apr 25

1/n Introducing ReDi (Representation Diffusion): a new generative approach that leverages a diffusion model to jointly capture
– Low-level image details (via VAE latents)
– High-level semantic features (via DINOv2)🧵

4 28

Sander Dieleman @sedielem.bsky.social · Apr 15

New blog post: let's talk about latents!
sander.ai/2025/04/15/l...

Generative modelling in latent space

Latent representations for generative models.

sander.ai

3 18 74

Sander Dieleman @sedielem.bsky.social · Apr 14

Amazing interview with Yang Song, one of the key researchers we have to thank for diffusion models.

The most important lesson: be fearless! The community's view on score matching was quite pessimistic at the time, he went against the grain and made it work at scale!

www.youtube.com/watch?v=ud6z...

History of Diffusion - Yang Song

YouTube video by Bain Capital Ventures

www.youtube.com

4 25

Reposted by Sander Dieleman

Jeff Dean @jeffdean.bsky.social · Mar 25

🥁Introducing Gemini 2.5, our most intelligent model with impressive capabilities in advanced reasoning and coding.

Now integrating thinking capabilities, 2.5 Pro Experimental is our most performant Gemini model yet. It’s #1 on the LM Arena leaderboard. 🥇

34 65 220

Sander Dieleman @sedielem.bsky.social · Feb 21

We are hiring on the Generative Media team in London: boards.greenhouse.io/deepmind/job...

We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.

Research Scientist, Generative Media

London, UK

boards.greenhouse.io

4 12 35

Sander Dieleman @sedielem.bsky.social · Feb 10

Great interview with @jascha.sohldickstein.com about diffusion models! This is the first in a series: similar interviews with Yang Song and yours truly will follow soon.

(One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)

History of Diffusion - Jascha Sohl-Dickstein

YouTube video by Bain Capital Ventures

www.youtube.com

11 44

Sander Dieleman @sedielem.bsky.social · Jan 28

Yes! Also listen to this and contemplate the universe: grumusic.bandcamp.com/album/cosmog...

Cosmogenesis, by grumusic

8 track album

grumusic.bandcamp.com

1 3