🚨New paper led by Ariba Khan Lots of prior research has assumed that LLMs have stable preferences, align with coherent principles, or can be steered to represent specific worldviews. No ❌, no ❌, and definitely no ❌. We need to be careful not to anthropomorphize LLMs too much.

Another moment to be proud of an excellent team: Today the Pruna AI team has open sourced parts of their AI model optimization framework: github.com/PrunaAI/pruna/ If you care about more efficient and less costly models, and look for minimal overhead in development, check it out!

🚨 Update Alert! 🚨 • ⚡ Much faster loading (seconds, not minutes!) • ✨ Fresh layout for Large NLP Atlas • 📖 Clear explanations of all features Stay tuned—more improvements coming soon!

martenlienen.com/blog/what-is-d… A summary of my basic understanding of SDEs, Ito and Stratonovich integrals that I gathered from Applied Stochastic Differential Equations by Simo Särkkä and Arno Solin #math #machinelearning

The paper of my final "pure" physics project just got published in Nano Letters doi.org/10.1021/acs.na… joint work with Ludwig Burger, CLP, Hamid Seyed-Allaei Giovanni Giunta and Ulrich Gerland

I am truly excited to share our latest work with Michael Scherbela, Philipp Grohs, and Stephan Günnemann on "Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems"! arxiv.org/abs/2504.06087

Happy to share that our paper "Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space" got accepted to #ICLR2025, and we will be presenting it this week in Singapore! Joint work with Nicholas Gao, Tom Wollschläger, Johanna Sommer, and Stephan Günnemann. 🧵 1/

Excited to announce our #ICLR2025 spotlight work deriving the first exact certificates for neural networks against label poisoning 🎉. Joint work w/ Mahalakshmi Sabanayagam, Stephan Günnemann & Debarghya. For more details check out the thread below👇 or check out our paper arxiv.org/abs/2412.00537.

If you are attending #ICLR2025 and are interested in electronic structure modelling / quantum chemistry come by our poster on learnable non-local XC-functionals to discuss with Nicholas Gao and me. 🗓️ Today | 3:00 pm– 5:30 pm 📍Hall 3 | Poster #3

How do LLMs navigate refusal? Our new @ICMLConf paper introduces a gradient-based approach & Representational Independence to map this complex internal geometry. 🚨 New Research Thread! 🚨 The Geometry of Refusal in Large Language Models By Stephan Günnemann's lab & Google AI. 🧵👇

Real data is noisy but HiPPO assumes it's clean. Our UnHiPPO initialization resists noise with implicit Kalman filtering and makes SSMs robust without architecture changes. #ICML poster: Thu 11am E-2409 Paper: openreview.net/forum?id=U8GUm… Code: github.com/martenlienen/u… w/ Stephan Günnemann

Want to learn more about how to make self-supervised training on sequential data differentially private? Come by our #ICML2025 poster E-1007 in East Exhibition Hall A/B on Tuesday at 11am! #icml

Injecting structure into LLMs with no changes to the architecture? SAFT🧃 Structure-aware LLM fine-tuning for AMR-to-text. New SOTA + no model changes! 📍#SKnowLLM, KDD, Toronto 🇨🇦 🗓️ Aug 4, 1–5pm · Room 717 📄 arxiv.org/abs/2507.13381 w/ R. Kamel, Simon Geisler, Stephan Günnemann 1/5