Salva Rühling Cachay

A huge thank you to my brilliant collaborators
@nvidia -Miika Aittala, @karstenkreis.bsky.social, Noah Brenowitz, Arash Vahdat & Morteza Mardani-and
@yuqirose.bsky.social @ucsandiego.bsky.social

👇 See you next week in San Diego! Paper: arxiv.org/abs/2506.20024

𝗧𝗵𝗲 𝗥𝗲𝘀𝘂𝗹𝘁𝘀: 3) 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗥𝗲𝗮𝗹𝗶𝘀𝗺: ERDM matches the power spectra of operational physics-based models (IFS ENS), solving the "blurriness" problem common in AI weather models.

𝗧𝗵𝗲 𝗥𝗲𝘀𝘂𝗹𝘁𝘀: 1) Up to 🚀 𝟱𝟬% 𝗶𝗺𝗽𝗿𝗼𝘃𝗲𝗺𝗲𝗻𝘁 in probabilistic CRPS skill on Navier-Stokes dynamics, with strong calibratio; 2) Up to 🌍 10% improvement on ERA5 global weather forecasting (1.5° resolution) over autoregressive EDM baselines;

𝗢𝘂𝗿 𝗰𝗼𝗻𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻: We unify rolling diffusion with the high-fidelity design of EDM by adapting EDMs core components—noise schedule, loss weighting, sampler—and supplementing it with a hybrid 3D backbone and a simple but effective initialization strategy.

The Gap: Existing methods struggle to balance fidelity and efficiency.

❌ Autoregressive models ignore temporal dependencies & may accumulate error
❌ Full "video" diffusion is computational- and data-inefficient

We chose a third path: Rolling Diffusion—but gave it an upgrade..

🌍 Modeling chaos isn't just about predicting the next step—it's about modeling how uncertainty grows over time.🌪️

I’m thrilled to share Elucidated Rolling Diffusion Models (ERDM), accepted to #NeurIPS2025!

We unify rolling diffusion with EDM for forecasting complex systems🧵👇

Internship in our group at Mila in reinforcement learning + graphs for reducing energy use in buildings.

More info and submit an application by Jan 13 here:
forms.gle/TCChXnvSAHqz...

Questions? Email donna.vakalis@mila.quebec with [intern!] in the subject line.

Come talk to us tomorrow at Poster session 3: Thursday 11am-2pm at East Hall A-C #3905!

(Or ping me if you'd like to chat outside of the poster session!)

ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses Existing machine learning models of weather variability are not formulated to enable assessment of their response to varying external boundary conditions such as sea surface temperature and greenhouse...

The new ACE2 climate emulator from Oliver Watt-Meyer et al has very compelling results, with results that look comparable to NeuralGCM. Congrats to the AI2 team!
arxiv.org/abs/2411.112...

Thanks!

🙌🏽🙋🏽‍♂️

I made a starter pack for those working in or adjacent to Machine Learning for Earth System Modeling! Apologies if I forgot anyone, and feel free to suggest people to add :)

go.bsky.app/C5DQNCe