iiinova — where your digital self keeps evolving

Reposted by James Thornton

Arnaud Doucet @arnauddoucet.bsky.social · 15/11/2025

🔥 WANTED: Student Researcher to join me, @vdebortoli.bsky.social, Jiaxin Shi, Kevin Li and @arthurgretton.bsky.social in DeepMind London. You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...

google.com

Student Researcher, 2026 — Google Careers

03515

Reposted by James Thornton

TMLR Published Papers @tmlr-pub.bsky.social · 26/10/2025

New #J2C Certification: BM$^2$: Coupled Schrödinger Bridge Matching Stefano Peluchetti openreview.net/forum?id=fqkq1MgONB #schrödinger #bridges #bridge

011

Reposted by James Thornton

Andrew Campbell @arcampbell.bsky.social · 07/10/2025

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

0136

Reposted by James Thornton

NeurIPS Conference @neuripsconf.bsky.social · 01/10/2025

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.

0193

Reposted by James Thornton

Arthur Gretton @arthurgretton.bsky.social · 14/07/2025

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

083

Reposted by James Thornton

Sander Dieleman @sedielem.bsky.social · 14/05/2025

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!

youtube.com

History of Diffusion - Sander Dieleman

YouTube video by Bain Capital Ventures

0187

Reposted by James Thornton

Karsten Kreis @karstenkreis.bsky.social · 24/04/2025

🔥 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)

131

Reposted by James Thornton

Quentin Berthet @ AISTATS @qberthet.bsky.social · 17/04/2025

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.

3174

Reposted by James Thornton

Josh Susskind @kindsuss.bsky.social · 11/04/2025

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!

065

James Thornton @jamesthornton.bsky.social · 06/04/2025

“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

130

Reposted by James Thornton

Serge Belongie @serge.belongie.com · 30/03/2025

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)

docs.google.com

NeurIPS participation in Europe

We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

6279161

Reposted by James Thornton

Alexandre Ramé @ramealexandre.bsky.social · 26/03/2025

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!

041

Reposted by James Thornton

Sander Dieleman @sedielem.bsky.social · 21/02/2025

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.

boards.greenhouse.io

Research Scientist, Generative Media

London, UK

43612

Reposted by James Thornton

Adrien Corenflos @adriencorenflos.bsky.social · 20/02/2025

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...

zz.zabemon.com

The personal website of Zheng Zhao

195

Reposted by James Thornton

Preetum Nakkiran @preetumnakkiran.bsky.social · 11/02/2025

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/

Left Image: A shaggy dog-horse hybrid standing in a rural landscape.
Right Image: A golden dog wearing a red beret against a blurred outdoor background.

23915

Reposted by James Thornton

Sander Dieleman @sedielem.bsky.social · 10/02/2025

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 🥲)

youtube.com

History of Diffusion - Jascha Sohl-Dickstein

YouTube video by Bain Capital Ventures

04311

Reposted by James Thornton

Preetum Nakkiran @preetumnakkiran.bsky.social · 10/02/2025

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

1624

Reposted by James Thornton

Adam Johansen @adamjohansen.bsky.social · 08/02/2025

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

rss.org.uk

2nd RSS/Turing Workshop on Gradient Flows for Sampling, Inference, and Learning

3127

Reposted by James Thornton

lebellig @lebellig.bsky.social · 06/02/2025

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

2142

Reposted by James Thornton

Samira @samiraabnar.bsky.social · 28/01/2025

🚨 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:

1188

Reposted by James Thornton

Conor Durkan @conormdurkan.bsky.social · 21/01/2025

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...

pxgy.substack.com

Thoughts on generative music

Observations from a year building generative music tech

011

Reposted by James Thornton

David Pfau @davidpfau.com · 18/01/2025

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.

49511

Reposted by James Thornton

Edouard Grave @exgrv.bsky.social · 13/01/2025

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… 🟢

071

Reposted by James Thornton

Brandon Amos @bdamos.bsky.social · 06/01/2025

📢 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...

metacareers.com

Postdoctoral Researcher, Fundamental AI Research (PhD)

Meta's mission is to build the future of human connection and the technology that makes it possible.

15312

Reposted by James Thornton

arxiv stat.ML @arxiv-stat-ml.bsky.social · 25/12/2024

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

086

Reposted by James Thornton

Sander Dieleman @sedielem.bsky.social · 16/12/2024

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...

blog.google

State-of-the-art video and image generation with Veo 2 and Imagen 3

We’re rolling out a new, state-of-the-art video model, Veo 2, and updates to Imagen 3. Plus, check out our new experiment, Whisk.

06017

Reposted by James Thornton

Arnaud Doucet @arnauddoucet.bsky.social · 15/12/2024

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...

drive.google.com

BreimanLectureNeurIPS2024_Doucet.pdf

932868

Reposted by James Thornton

Paul Vicol @paulvicol.bsky.social · 14/12/2024

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

061

Reposted by James Thornton

NeurIPS Conference @neuripsconf.bsky.social · 12/12/2024

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

0403

Reposted by James Thornton

Alex Thiery @alexxthiery.bsky.social · 13/12/2024

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)

1494

Reposted by James Thornton

Sander Dieleman @sedielem.bsky.social · 15/11/2024

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? 🤔

3412836

Reposted by James Thornton

Miguel Angel Bautista @itsbautistam.bsky.social · 06/12/2024

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!

142

Reposted by James Thornton

lebellig @lebellig.bsky.social · 30/11/2024

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.

2414