iiinova — where your digital self keeps evolving

Reposted by Francesco Immorlano

Felix Draxler @drrelax.bsky.social · 22/04/2026

LLMs are autoregressive and slow? No! Parallel Token Prediction decodes multiple consistent tokens in one model call. PTP allows arbitrary dependencies in one call, unlike discrete diffusion. Practical: 2.4x speedup github.com/mandt-lab/ptp ICLR: Apr 23, morning poster P3-#608

1295

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

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: www.pnas.org/doi/10.1073/...

pnas.org

Transferring climate change physical knowledge | PNAS

Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertaint...

000

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

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

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

📊 Harnessing observations is critical. Since even high-resolution models are imperfect, effectively leveraging observational data through AI-empowered data assimilation becomes crucial for improving model accuracy and reliability. 🧵 6/n

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

⚙️ Differentiable physics is essential. There’s a pressing need to redesign physics-based models so that they are differentiable, enabling seamless integration with AI frameworks. 🧵 5/n

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

Here are some of my key takeaways: 🔗 Hybrid approaches are the future. Rather than relying solely on physics-based models or purely data-driven approaches, the real breakthrough lies in combining both approaches to unlock the best of both worlds. 🧵 4/n

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

The symposium featured an inspiring lineup of talks that showcased the massive developments happening at the intersection of AI and climate science. 🧵 3/n

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

The poster session was exciting. I had the chance to connect with fantastic researchers, many of whom showed genuine interest in my work and engaged in meaningful discussions. 🧵 2/n

100

Francesco Immorlano @f-immorlano.bsky.social · 06/06/2025

Just got back from an incredible experience at the EXCLAIM symposium “Is AI the Future of Weather and Climate Modeling?” at the @ethz.ch. 🧵 1/n

120

Francesco Immorlano @f-immorlano.bsky.social · 09/04/2025

Truly grateful to my mentors - Pierre Gentine, Giovanni Aloisio, and Stephan Mandt - and to the co-authors for their support and the opportunity to work on such an amazing project at the intersection of AI and climate. 🧵 4/4

110

Francesco Immorlano @f-immorlano.bsky.social · 09/04/2025

In this work, we use a Transfer Learning strategy to constrain CMIP6 simulations to historical observations, ultimately providing more precise and reliable estimates of global warming spatially resolved on global and regional scales. 🧵 3/4

110

Francesco Immorlano @f-immorlano.bsky.social · 09/04/2025

Earth System Models are currently the main tools used to project climate change according to future emission pathways. However, they still exhibit large uncertainties which are a major roadblock for policymakers. 🧵 2/4

110

Reposted by Francesco Immorlano

Pierre Gentine @pierregentine.bsky.social · 08/04/2025

So delighted to share our new paper, my little Covid project brought to a whole new level by Francesco Immorlano www.pnas.org/doi/10.1073/.... We demonstrate how future projections can be refined using transfer learning (fine tuning). This refines our estimates of global warming.

pnas.org

PNAS

Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...

0143

Reposted by Francesco Immorlano

LEAP-STC @leapstc.bsky.social · 22/02/2025

Our Dep. Dir. Tian Zheng connected w/Cali LEAPers @jlin404.com + @f-immorlano.bsky.social and other colleagues (Katherine Frields, Liran Peng, Yan Xia) while at an event near @ucirvine.bsky.social ... Just proves: science = more fun together! 💪 #LEAPcolors #community #ML #AI #physics #data #climate

032

Reposted by Francesco Immorlano

Pierre Gentine @pierregentine.bsky.social · 21/02/2025

Excited to share some great collaboration on a new data assimilation framework with transformer encoding arxiv.org/pdf/2502.02884. Exciting times for data assimilation with ML

arxiv.org

172

Reposted by Francesco Immorlano

Padhraic Smyth @padhraicsmyth.bsky.social · 22/01/2025

New postdoc position open at UCI to work at the intersection of machine learning and climate science, jointly between Stephan Mandt's group and my group. More details and application information here: ics.uci.edu/~smyth/postd... Feel free to share.

042

Reposted by Francesco Immorlano

Bart Verheggen @bverheggen.bsky.social · 12/01/2025

"Extreme wet-to-dry transitions can amplify wildfire risk by allowing increased rates of plant growth to be immediately followed by rapid drying of flammable vegetation, increasing the potential intensity of subsequent fire events" www.nature.com/articles/s43... @weatherwest.bsky.social

nature.com

Hydroclimate volatility on a warming Earth - Nature Reviews Earth & Environment

Rapid transitions between extreme wet and extreme dry conditions — ‘hydroclimate whiplash’ — have marked environmental and societal impacts. This Review outlines observed and projected changes in hydr...

082

Reposted by Francesco Immorlano

Padhraic Smyth @padhraicsmyth.bsky.social · 23/12/2024

Pictures from the recent UCI Social at @neuripsconf.bsky.social with a subset of students, faculty, guests. Looking forward to the next event at NeurIPS 2025 in San Diego!

group photo at UCI Social event, NeurIPS 2024

Faculty + guest at UCI Social at NeurIPS 2024

062

Reposted by Francesco Immorlano

LEAP-STC @leapstc.bsky.social · 14/12/2024

We spy @f-immorlano.bsky.social + LEAP alum Sungduk Yu, who supported @juannat7.bsky.social @ #NeurIPS2024: "ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction." #NSF #CUSEAS @neuripsconf.bsky.social @columbiaclimate.bsky.social @ucirvine.bsky.social

1101