📄 openreview.net/forum?id=btJ...

Special thanks to our co-authors @nfel.bsky.social @kirillbykov.bsky.social @philinelb.bsky.social Anna Hedström, and Marina Höhne who are not with us in person at the conference.

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
@lkopf.bsky.social @nfel.bsky.social @kirillbykov.bsky.social @philinelb.bsky.social Anna Hedström, Marina Höhne @eberleoliver.bsky.social
👇

I’m thrilled to be co-convening a session at #EGU2026 focused on forecast verification of AI-based weather models 🌦️
If your research bridges AI weather forecasts + XAI/statistical verification don’t hesitate to submit: meetingorganizer.copernicus.org/EGU26/sessio...
🌍 #verification #AIweather #EGU26

What an amazing work and team!🎉

We are excited to discus’s Polysemanticity @neuripsconf.bsky.social with you! 🧠

Check out the paper at the link below!

Many Thanks to my co-authors @marleneclimate.bsky.social
@fionaspuler.bsky.social @kirillbykov.bsky.social and Marina M.-C. Höhne

We asses questions such as: can deep learning boost S2S forecasts and leverage teleconnections?

🚨New paper 🚨

We are happy to announce that our paper “Deep Learning meets Teleconnections: Improving S2S Predictions for European Winter Weather” has been published at Machine Learning: Earth @ioppublishing.bsky.social

📄 iopscience.iop.org/article/10.1...

💻 github.com/philine-bomm...

With PRISM you can investigate polysemanticity and have access to more detailed descriptions of the neuron’s purpose.

I am so happy to have contributed to this work.

🚨Preprint alert 🚨

Why limit our view to a single concept when neurons potentially encode multiple concepts? 👀

Check out 🔎PRISM🔎, our new multi-concept interpretability framework for LLMs.

Congratulations to @lkopf.bsky.social and the team!

📄: arxiv.org/abs/2506.15538

Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather Predictions on subseasonal-to-seasonal (S2S) timescales--ranging from two weeks to two month--are crucial for early warning systems but remain challenging owing to chaos in the climate system. Telecon...

🚨new preprint alert🚨

Can deep learning boost S2S forecasts? We investigated how to leverage teleconnections to improve deep learning predictions! #AI #Weather #Climate

📄: arxiv.org/abs/2504.07625
💻: (coming soon) github.com/philine-bomm...

GitHub - annahedstroem/GEF: Code and notebooks to paper "Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions" (TMLR, 2025) Code and notebooks to paper "Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions" (TMLR, 2025) - annahedstroem/GEF

Code: github.com/annahedstroe...

🚨 New paper alert! 🚨

We’re excited to share our latest work on interpretability evaluation:

"Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions"

📜 Accepted at TMLR 🎉
🔥 Survey certification 🔥
📖 Read: openreview.net/pdf?id=ukLxqA8…

I had an amazing experience at my first #AGU24 and enjoyed to finally meet so many great researchers in person. I am excited to see what the future holds for #climateAI and #climatescience 💪🏼💡💻🌎🌍🌏