Research Scientist @GoogleDeepMind, PhD Student @AmlabUva, @ai4science_lab @UvA_Amsterdam. Previously @MSFTResearch @FlatironInst
Joined December 2012
- Tweets191
- Following434
- Followers1.6K
- Likes1.5K
David Ruhe retweeted
As if we needed any more evidence that 2026 is the year of continuous diffusion for language🤭
(I recently wrote a blog post about my thoughts on this topic, in case you missed it: sander.ai/2026/08/24/continu…)
💫 Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
📈 Comparable with discrete dLMs and AR on math and coding
🎛️ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
David Ruhe retweeted
💫 Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
📈 Comparable with discrete dLMs and AR on math and coding
🎛️ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
Introducing 💫 Gumbel Straight Flow 💫: Distilling Autoregressive Models into One-step Flow Maps 🚀
Can autoregressive (language) models be used as teachers for flow map parallel samplers?
📄 Paper: arxiv.org/abs/2610.00497
Huge thanks to our amazing intern @k01047339268, and to co-authors @ArnaudDoucet1 , @AndrewC_ML , @ValentinDeBort1 , and Thomas Mensink!
Tagging people who might be interested @sitanch @msalbergo @nmboffi @FEijkelboom @HannesStaerk @yjelid @LucaAmb @njwfish @json_yim @MoleiTaoMath @_sophia_tang_ @PatrickPyn35903 @k_neklyudov @samsongvch @FrancoisRozet @ssahoo_ @zhihanyang_ @ShamKakade6 @Jaeyeon_Kim_0
David Ruhe retweeted
⚡️Few-step diffusion without a teacher, self-distillation or JVPs.
iDDM: a single model trained from scratch in one stage. ImageNet-256: 4.48 FID at 4 steps and 2.38 at 50, from the same checkpoint
🧵 (1/6)
David Ruhe retweeted
Today, we're opening ElevenLabs Netherlands 🇳🇱!
We're building an incredible team here and opening an office in Amsterdam. If you're interested in working with us, get in touch!
David Ruhe retweeted
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon!
It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback.
Here’s a look at the benchmarks:
David Ruhe retweeted
🔥Welcome 🔺Simplex Diffusion Models🔻!
Standard discrete diffusion models suffer from "information collapse" because they discard uncertainty at intermediate steps by sampling categorical tokens. (1/5)
David Ruhe retweeted
🔺Happy to share a project done during my internship🔻 It was amazing to collaborate 🥹 @ValentinDeBort1 @ArnaudDoucet1 @agalashov @AndrewC_ML @JamesTThorn and Kevin Li (who I cannot find on Twitter)
David Ruhe retweeted
Today we’re launching Gemini 3.8 Flash Cyber and Gemini 3.8 Flash. ⚡️🛡️
3.8 Flash Cyber is our most capable cybersecurity model for finding and fixing vulnerabilities. It sits on the Pareto Frontier on CWE-Bench for patching. Available to trusted defenders through our new Fairwind Program.
David Ruhe retweeted
New blog post: continuous diffusion for language is back!
This research direction receded into the background for a while, but as of this year, it is once again a hot topic. I wrote down a historical perspective and some thoughts on the recent revival.
sander.ai/2026/08/24/continu…
David Ruhe retweeted
Our tech report on DiffusionGemma is out! 🚀
My biggest highlight? Online post-training is a game changer for text diffusion.
We performed joint Sampler Distillation and Reinforcement Learning (SD⋅RL) after SFT, pushing the quality-speed Pareto frontier into a new regime 📈
David Ruhe retweeted
We just released the DiffusionGemma tech report. Text diffusion models open up a radically different part of the latency–quality Pareto frontier 👇
We hope the report makes it easier for researchers and engineers to understand the model, build on it, and create things we haven’t thought of yet.
None of this work happened in isolation. DiffusionGemma builds on years of amazing research from the text diffusion community, and we wanted the report to recognise that. We’re standing on the shoulders of giants❤️
Let’s keep pushing towards lower-latency, higher-quality LLMs together!
David Ruhe retweeted
Super cool work by @GrigoryBartosh thoroughly exploring the options for cheaper generation with diffusion models ✨
🚀 Excited to share my @GoogleDeepMind student researcher project: Dual-Rate Diffusion✨
⚡ A simple construction that speeds up both regular diffusion and distilled models by interleaving a heavy context encoder with a light conditional denoiser.
🧵👇
Check out @GrigoryBartosh 's awesome Student Researcher project on making diffusion models (and their distilled variants) more lightweight!
🚀 Excited to share my @GoogleDeepMind student researcher project: Dual-Rate Diffusion✨
⚡ A simple construction that speeds up both regular diffusion and distilled models by interleaving a heavy context encoder with a light conditional denoiser.
🧵👇
Awesome effort by Emiel in writing a blog post about our recent work. The Gen.Perplexity vs. Entropy plot is especially revealing!
New blog post on our recent paper: Beyond Single Tokens, Distilling Discrete Diffusion.
D-MMD lands on the Pareto frontier of gen PPL vs. diversity, outperforming continuous diffusion distillation approaches — while staying native to discrete tokens.
ehoogeboom.github.io/post/di…
