Very excited to share our preprint: Self-Speculative Masked Diffusions We speed up sampling of masked diffusion models by ~2x by using speculative sampling and a hybrid non-causal / causal transformer arxiv.org/abs/2510.03929 w/ @vdebortoli.bsky.social, Jiaxin Shi, @arnauddoucet.bsky.social

We are disappointed that some community members have been sending threatening messages to organizers after decisions. While we always welcome feedback, our organizers are volunteers from the community, and such messages will not be tolerated and may be investigated as code of conduct violations.

Distributional diffusion models with scoring rules at #icml25 Fewer, larger denoising steps using distributional losses! Wednesday 11am poster E-1910 arxiv.org/pdf/2502.02483 @vdebortoli.bsky.social Galashov Guntupalli Zhou @sirbayes.bsky.social @arnauddoucet.bsky.social

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!

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

🔥 I'm at ICLR'25 in Singapore this week - happy to chat! 📜 With wonderful co-authors, I'm co-presenting 4 main conference papers and 3 @gembioworkshop.bsky.social papers (gembio.ai), and I contribute to a panel (synthetic-data-iclr.github.io). 🧵 Overview in thread. (1/n)

I will be attending #ICLR2025 in Singapore and #AISTATS2025 in Mai Khao over the next two weeks. Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.

Check out our Apple research work on scaling laws for native multimodal models! Combined with mixtures of experts, native models develop both specialized and multimodal representations! Lots of rich findings and opportunists for follow up research!

“serious [research] as opposed to .. only reason is to produce another paper” I have dismissed some ideas, later published and turned out to be impactful ICML reviewing and 2/4 papers are a rehash of existing work, the only purpose is CV padding .. perhaps a necessary evil but frustrating

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

Hiring two student researchers for Gemma post-training team at @GoogleDeepMind Paris! First topic is about diversity in RL for LLMs (merging, generalization, exploration & creativity), second is about distillation. Ideal if you're finishing PhD. DMs open!

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.

A co-author (and friend!) is hiring his first post doc in Linköping University, Sweden. It seems the application deadline is not settled yet, so you have *plenty of time* to c̶o̶n̶s̶i̶d̶e̶r̶ applyi̶n̶g̶ ! The department is strong and so is he. zz.zabemon.com/blogs/2025/0...

Paper🧵 (cross-posted at X): When does composition of diffusion models "work"? Intuitively, the reason dog+hat works and dog+horse doesn’t has something to do with independence between the concepts being composed. The tricky part is to formalize exactly what this means. 1/

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 🥲)

finally managed to sneak my dog into a paper: arxiv.org/abs/2502.04549

Registration is now open for the 2nd RSS/Turing Workshop on Gradient Flows for Sampling, Inference, and Learning at rss.org.uk/training-eve.... Date: Monday 24 March 2025, 10.00AM - 5.00PM Location: The Alan Turing Institute

I'm increasingly uncomfortable with the argument (read more and more often) that rectified flow (without reflow steps) offers straighter trajectories than diffusion (in the Gaussian case), despite being a diffusion model itself with special noise schedule... It seems it comes from the confusion 1/2

🚨 One question that has always intrigued me is the role of different ways to increase a model's capacity: parameters, parallelizable compute, or sequential compute? We explored this through the lens of MoEs:

I wrote up some thoughts having worked on generative music over the past year. I talk a bit about where tech is now, how it's being used, and where it might go. pxgy.substack.com/p/thoughts-o...

The thing about "AI progress is hitting a wall" is that AI progress (like most scientific research) is a maze, and the way you solve a maze is by constantly hitting walls and changing directions.

Excited to release a preview of Helium-1, our 2B LLM targeting edge and mobile devices. 🚀 More to come in the future: training code, support for more languages, data pipeline, tech report & more… 🟢

📢 My team at Meta (including Yaron Lipman and Ricky Chen) is hiring a postdoctoral researcher to help us build the next generation of flow, transport, and diffusion models! Please apply here and message me: www.metacareers.com/jobs/1459691...

O. Deniz Akyildiz, Pierre Del Moral, Joaqu\'in Miguez Gaussian entropic optimal transport: Schr\"odinger bridges and the Sinkhorn algorithm https://arxiv.org/abs/2412.18432

Here's Veo 2, the latest version of our video generation model, as well as a substantial upgrade for Imagen 3 🧑‍🍳🚢 (Did I mention we are hiring on the Generative Media team, btw 👀) blog.google/technology/g...

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here drive.google.com/file/d/1eLa3...

@sedielem.bsky.social speaking now on Multimodal Iterative Refinement at the Adaptive Foundation Models workshop!

Live! Keynote talk by Arnaud Doucet From Diffusion Models to Schrödinger Bridges West Exhibition Hall C, B3 https://buff.ly/4ga9GD7

Fantastic #neurips keynote by Arnaud Doucet! Really like this slide tracing back many of the modern flow-matching / stochastic interpolants ideas to a 1986 result by probabilist Istvan Gyongy describing how to "Markovianize" a diffusion process (eg. having coefficients depending on all the past)

In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome! I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔

Here's one to read on your flight to #NeurIPS2024! A flow-matching transformer model in function space! This model has all the advantages of neural fields: resolution-free generation and domain-agnostic architecture, while obtaining strong results on ImageNet-256 and Objaverse!

Important to keep in mind when reading about diffusion or flow matching: - diffusion models's Probability Flow ODE is not optimal transport. - Composition of optimal transports is not optimal. - Flow matching with OT conditional paths doesn’t provide optimal transport.