Eike Eberhard

While Nicholas is switching gears, I am switching fields from Physics to Machine Learning. This started out as a curious open-ended project, but it turns out that GNNs might be able to advance DFT, too. I can‘t wait to find out where this line of research might lead us.

Excited to share that my first PhD paper, which introduces a new diffusion model for relational databases, has been accepted to #NeurIPS2025! We will be presenting it this week in San Diego. ☀️🌴 Joint work with @ludke_david, @SchwinnLeo, and @guennemann. 🧵 1/

Heading to San Diego for #NeurIPS2025! 🌴☀️ I’ll be presenting 3 recent papers covering generative models for hierarchies, spatiotemporal tissue dynamics, and long-range graph learning. If you're around, drop by and say hi! 👋 Here’s the schedule 🧵👇

@k_sakalyan @ale__palmaa @guerrantif @fabian_theis @guennemann @TU_Muenchen @HelmholtzMunich @MunichCenterML @MdsiTum Finally, a contemporary method to study cell differentiation and growth mechanisms, instead of cellular automata approaches🥳

Our paper “Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow” has been accepted at #NeurIPS2025! @ale__palmaa @guerrantif @fabian_theis @guennemann (@TU_Muenchen × @HelmholtzMunich × @MunichCenterML × @MdsiTum ) 🧵

@timtomov @dfuchsgruber @TomWollschlager @guennemann Interesting how all current estimators fail once we have ambiguity in the ground truth

Can we actually tell when LLMs know or don’t know? For questions with a single answer, that works. But once ambiguity enters - several answers are correct - current methods collapse, confusing model with data uncertainty. w/ @dfuchsgruber @TomWollschlager @guennemann [1/4]🧵

We can sample highly transferable jailbreaks directly from non-autoregressive models (e.g., Diffusion LLMs) without any optimization!

Open-source Diffusion LLMs easily break GPT-5! In “Diffusion LLMs are Natural Adversaries for any LLM,” we show that Inpainting on Diffusion LLMs yields efficient, transferable jailbreaks without any model access. @TomWollschlager, Paul Ungermann, @guennemann, @leoschwinn 🧵

📣 The Call for Blog Posts for #ICLR2026 is now live: iclr.cc/Conferences/20… We look forward to your submissions! Questions? DM me or email: blogpost-chairs@iclr.cc

The hunt for increased WL expressivity has led to many new GNNs but limited real-world success. So what are we missing? Can we find a better objective? We answer these questions in our new paper: arxiv.org/abs/2509.01254 Joint work /w @TomWollschlager @guennemann 🧵 (1/6)

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, @geisler_si, @guennemann 1/5

Super excited to be at #ICML2025 in Vancouver this week! 🇨🇦 Thrilled to be presenting new work and soaking in all the amazing research. This also marks my first conference trip since joining @GoogleResearch a couple of months ago! #LLMs #AIResearch

How private is DP-SGD for self-supervised training on sequences? Our #ICML2025 spotlight shows that it can be very private—if you parameterize it right! 📜arxiv.org/abs/2502.02410 #icml Joint work w/ M. Dalirrooyfard, J. Guzelkabaagac, A. Schneider, Y. Nevmyvaka, @guennemann 1/6

🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT. ⚛️🔥🧪🧬

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 @guennemann's lab & @GoogleAI. 🧵👇

3️⃣ Key Question ❓ Is refusal behavior governed by a single vector, or do multiple independent mechanisms exist? We introduce a novel gradient-based method to extract refusal-mediating directions more effectively! 🎯

This ICLR is the best conference ever. Attendees are extremely friendly and cuddly. ..What do you mean this is the wrong hall?

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 @n_gao96 and me. 🗓️ Today | 3:00 pm– 5:30 pm 📍Hall 3 | Poster #3

Thrilled to announce that we just presented „MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds“ at #ICLR2025 🧲 @j_m_sommer @Pseudomanifold @fabian_theis @guennemann For those who couldn’t make it to our spotlight: openreview.net/forum?id=5FXKg…

Excited to announce our #ICLR2025 spotlight work deriving the first exact certificates for neural networks against label poisoning 🎉. Joint work w/ @maha81193, @guennemann & Debarghya. For more details check out the thread below👇 or check out our paper arxiv.org/abs/2412.00537.