Thank you to the amazing co-authors I am honoured to work with!
Elijah Tavares, @FelixDrRelax, @juannat7, Violette Launeau, Duncan Watson-Parris, Padhraic Smyth, Pierre Gentine, @StephanMandt
17 climate models, 17 different futures, and 1 observed past that reveals models’ biases. How confident can we be in climate projections?
New preprint: diffusion guidance steers a generative emulator of 17 CMIP6 models toward observations
📑 → https://t.co/7F3si91OPX
🧵 1/4
Our paper "Trading off Controllability and Realism in Generative Physics Emulators" received an Outstanding Paper Award at the AI4Physics Workshop at #ICML 2026. Congrats to my co-authors, especially lead authors @f_immorlano and Elijah Tavares!
AI for science needs calibrated models and uncertainty, but we show standard test-time diffusion guidance methods miss the Bayesian posterior. Our Calibrated Bayesian Guidance (CBG) fixes this, enabling Bayesian inference and setting a new SOTA for black-hole imaging.
Excited to see seven years of work come together: we can now consistently predict thermodynamic properties of fluid mixtures directly from molecular structure using machine learning. 🧪🤖
Our latest work just got accepted at Nature Communications: https://t.co/UcvrKvhbjo (1/4)
Recently gave a LEAP lecture at @Columbia and at @UCLA on a question I’m excited about: How can we design diffusion models for scientific inference—uncertainty-aware, calibrated, steerable, and heavy-tailed? https://t.co/iQhbpfdPD7
#HBD to arXiv!🎈
On August 14, 1991, the very first paper was submitted to arXiv. That's 34 years of sharing research quickly, freely & openly!
Some baby pictures to show how far we've come . . . when we were just a computer under desk . . . & in our 1994 punk phase . . . 👶💾
If you’re curious about my research, feel free to check out the paper. I’m always happy to chat, so please don't hesitate to reach out!
📑 Paper: https://t.co/pErMsf4bji
Huge thanks to the Center for Climate Systems Modeling (C2SM) and the EXCLAIM team for organizing such a well-curated event with an amazing agenda. It was an honor to be part of it.
🧵 7/n
I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models.
Sampling is actually being done in the browser using Tensorflow.js!
It is still in the very early stages.