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
07.10.2025 22:09 — 👍 13 🔁 6 💬 0 📌 0
doing a phd in RL/online learning on questions related to exploration and adaptivity
> https://antoine-moulin.github.io/
Machine learning researcher at Microsoft Research. Adjunct professor at Stanford.
Research fellow @OxfordStats @OxCSML, spent time at FAIR and MSR
Former quant 📈 (@GoldmanSachs), former former gymnast 🤸♀️
My opinions are my own
🇧🇬-🇬🇧 sh/ssh
Asst. Prof. in Machine Learning at UofT. #LongCOVID patient.
https://www.cs.toronto.edu/~cmaddis/
Research scientist at Anthropic. Prev. Google Brain/DeepMind, founding team OpenAI. Computer scientist; inventor of the VAE, Adam optimizer, and other methods. ML PhD. Website: dpkingma.com
Research scientist at Google DeepMind. Creating noise from data.
postdoc @ uni oxford. machine learning. climate. statistics.
web: treigerm.github.io
VP of AI Research, Principal Scientist @ EIT Oxford | ex-Director @ DeepMind Building models to accelerate fundamental sciences and medicine.
Opinions my own.
https://danilorezende.com/
Assistant Professor, University of Toronto.
Junior Research Fellow, Trinity College, Cambridge.
AI Fellow, Georgetown University.
Probabilistic Machine Learning, AI Safety & AI Governance.
Prev: Oxford, Yale, UC Berkeley, NYU.
https://timrudner.com
Machine Learning researcher at @Xaira_Thera (former @CambridgeEllis and @OxCSML) opinions expressed are my own.
Apple ML Research in Barcelona, prev OxCSML InfAtEd, part of MLinPL & polonium_org 🇵🇱, sometimes funny
Meta-constructor of constructive processes. Fascinated by destruction and the emergence of garbage.
Computational protein engineering & synthetic biochemistry at Takeda
Opinions my own
https://linktr.ee/ddelalamo
(ML ∪ Bayesian optimization ∪ active learning) ∩ (drug discovery)
Researcher @valenceai.bsky.social
Details: austintripp.ca
PhD student @MIT • Research on Generative Models for Biophysics and Drug Discovery
PhD candidate at MIT CSAIL. Generative models, protein design.
Ex: DeepMind, Microsoft, Instagram, Johns Hopkins University.
Website: https://people.csail.mit.edu/jyim/
X: https://x.com/json_yim
Sr Researcher at Microsoft Research AI for Science
Former Oxford Stats PhD in Bayesian Experimental Design
