James Thornton
@jamesthornton.bsky.social
Research scientist at Google DeepMind. Creating noise from data.
Reposted by James Thornton
🔥 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...
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
Student Researcher, 2026 — Google Careers
google.com
November 15, 2025 at 5:23 PM
🔥 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...
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
Reposted by James Thornton
New #J2C Certification:
BM$^2$: Coupled Schrödinger Bridge Matching
Stefano Peluchetti
https://openreview.net/forum?id=fqkq1MgONB
#schrödinger #bridges #bridge
BM$^2$: Coupled Schrödinger Bridge Matching
Stefano Peluchetti
https://openreview.net/forum?id=fqkq1MgONB
#schrödinger #bridges #bridge
October 26, 2025 at 12:23 PM
New #J2C Certification:
BM$^2$: Coupled Schrödinger Bridge Matching
Stefano Peluchetti
https://openreview.net/forum?id=fqkq1MgONB
#schrödinger #bridges #bridge
BM$^2$: Coupled Schrödinger Bridge Matching
Stefano Peluchetti
https://openreview.net/forum?id=fqkq1MgONB
#schrödinger #bridges #bridge
Reposted by James Thornton
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 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
October 7, 2025 at 10:09 PM
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 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
Reposted by James Thornton
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.
October 1, 2025 at 3:06 PM
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.
Reposted by James Thornton
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
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
July 14, 2025 at 12:57 PM
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
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
Reposted by James Thornton
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!
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
May 14, 2025 at 4:11 PM
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!
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!
Reposted by James Thornton
New blog post: let's talk about latents!
sander.ai/2025/04/15/l...
sander.ai/2025/04/15/l...
Generative modelling in latent space
Latent representations for generative models.
sander.ai
April 15, 2025 at 9:40 AM
New blog post: let's talk about latents!
sander.ai/2025/04/15/l...
sander.ai/2025/04/15/l...
Reposted by James Thornton
🔥 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)
📜 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)
April 24, 2025 at 8:17 AM
🔥 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)
📜 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)
Reposted by James Thornton
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.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
April 17, 2025 at 12:50 PM
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.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
Reposted by James Thornton
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!
Shukor, Fini, da Costa, Cord, Susskind, El-Nouby: Scaling Laws for Native Multimodal Models Scaling Laws for Native Multimodal Models https://arxiv.org/abs/2504.07951 https://arxiv.org/pdf/2504.07951 https://arxiv.org/html/2504.07951
April 11, 2025 at 10:37 PM
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
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
April 6, 2025 at 10:48 AM
“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
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
Reposted by James Thornton
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)
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 ...
docs.google.com
March 30, 2025 at 6:04 PM
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)
Reposted by James Thornton
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!
March 26, 2025 at 4:24 PM
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!
Reposted by James Thornton
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.
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
February 21, 2025 at 7:00 PM
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.
We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.
Reposted by James Thornton
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/blogs/2025/0...
The personal website of Zheng Zhao
zz.zabemon.com
February 20, 2025 at 11:48 AM
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/blogs/2025/0...
Reposted by James Thornton
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/
February 11, 2025 at 5:59 AM
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/
Reposted by James Thornton
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 🥲)
(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
February 10, 2025 at 10:28 PM
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 🥲)
(One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)
Reposted by James Thornton
finally managed to sneak my dog into a paper: arxiv.org/abs/2502.04549
February 10, 2025 at 5:03 AM
finally managed to sneak my dog into a paper: arxiv.org/abs/2502.04549
Reposted by James Thornton
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
Date: Monday 24 March 2025, 10.00AM - 5.00PM
Location: The Alan Turing Institute
2nd RSS/Turing Workshop on Gradient Flows for Sampling, Inference, and Learning
rss.org.uk
February 8, 2025 at 5:46 PM
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
Date: Monday 24 March 2025, 10.00AM - 5.00PM
Location: The Alan Turing Institute
Reposted by James Thornton
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
February 6, 2025 at 9:18 AM
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
Reposted by James Thornton
🚨 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:
We explored this through the lens of MoEs:
January 28, 2025 at 6:26 AM
🚨 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:
We explored this through the lens of MoEs:
Reposted by James Thornton
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...
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...
Thoughts on generative music
Observations from a year building generative music tech
pxgy.substack.com
January 21, 2025 at 3:36 PM
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...
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...
Reposted by James Thornton
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.
January 18, 2025 at 3:45 PM
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.
Reposted by James Thornton
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… 🟢
More to come in the future: training code, support for more languages, data pipeline, tech report & more… 🟢
Meet Helium-1 preview, our 2B multi-lingual LLM, targeting edge and mobile devices, released under a CC-BY license. Start building with it today!
huggingface.co/kyutai/heliu...
huggingface.co/kyutai/heliu...
kyutai/helium-1-preview-2b · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 13, 2025 at 6:24 PM
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… 🟢
More to come in the future: training code, support for more languages, data pipeline, tech report & more… 🟢
Reposted by James Thornton
📢 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...
www.metacareers.com/jobs/1459691...
Postdoctoral Researcher, Fundamental AI Research (PhD)
Meta's mission is to build the future of human connection and the technology that makes it possible.
www.metacareers.com
January 6, 2025 at 5:37 PM
📢 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...
www.metacareers.com/jobs/1459691...