Dominik Fuchsgruber

Check out our latest work on using a task-dependent latent structure to improve LLM generations and uncertainty!

Are LLM outputs just language? We often don’t know what the answer to a question will be - but we do know its structure. Numbers, lists, sets, ... Our framework models outputs in their underlying structure for better answers + uncertainty. w/ @dfuchsgruber @guennemann [1/4]🧵

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.

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 @n_gao96, @TomWollschlager, @j_m_sommer, and @guennemann. 🧵 1/

I am truly excited to share our latest work with @MScherbela, @GrohsPhilipp, and @guennemann on "Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems"! arxiv.org/abs/2504.06087

The paper of my final "pure" physics project just got published in @NanoLetters doi.org/10.1021/acs.na… joint work with Ludwig Burger, @ceslopast, Hamid Seyed-Allaei @GiovanniGiunt20 and Ulrich Gerland

Do you think your LLM is robust?⚠️With current adversarial attacks it is hard to find out since they optimize the wrong thing! We fix this with our adaptive, semantic, and distributional objective. By @guennemann's lab & @GoogleAI, w/ @cais support Here's how we did it. 🧵

Safe and reliable machine learning has never been more relevant. However, at the same time, LLMs made robustness research **more complex, less reproducible, and harder-to-evaluate**. How can we enable research progress despite these challenges?🧵 @guennemann @gauthier_gidel

Congrats to my amazing PhD students: We have 9 papers accepted at #ICLR2025. Reliability, AI4Science, graphs, LLMs, and more (go.tum.de/936150). And if you follow the recent discussions about AI efficiency, you might like our blog and webinars (pruna.ai).

Super happy & honored that our work on certifying NNs against poisoning won the Best Paper Award @AdvMLFrontiers at #NeurIPS2024. Come by our poster 10:40am-12&4-5pm (or talk) tomorrow :) Joint work w/@maha81193, Debarghya Ghoshdastidar & @guennemann L: arxiv.org/pdf/2407.10867

Make sure to stop by our #NeurIPS poster on Spatio-Spectral Graph Neural Networks (S²GNNs)! An efficient synergy of spatially & spectrally parametrised graph convolutions. Joint work w/ @geisler_si @dan1elherbst @guennemann. 📎 openreview.net/pdf?id=Cb3kcwY… 📆 Dec 13, 11am, #4608

Pay our poster a visit if you want to know more!

🏃‍♂️Our model can applied both post-hoc at negligible cost to many popular GNNs! 🔦We also establish a connection to evidential learning that drastically improves the robustness to distribution shifts in terms of accuracy.

Excited to present our spotlight paper on uncertainty for GNNs at #NeurIPS! 📝Paper: openreview.net/pdf?id=6vNPPtW… 📆Come by our poster on Dec 12th at 11am! Thanks to my amazing collaborators @TomWollschlager and @guennemann!

Excited to present our work on Neural Pfaffians at #NeurIPS. 🗣️ Oral: Friday 3:30pm, East Ballroom A, B 📊 Post: Friday 4:30pm - 7:30pm, East Exhibit Hall A-C #3600 📝 Paper: openreview.net/forum?id=HRkni… Happy to chat!

This week, we will present our recent #NeurIPS2024 paper.  📎 Paper: openreview.net/forum?id=HeoRs…  📆 Make sure to visit our poster #2600 on Fri, 13 December at 11 am!  Joint work with my amazing mentors @leon_het @j_m_sommer @fabian_theis @guennemann

Next week, I'll present our recent paper at NeurIPS 2024 in Vancouver. Many thanks to my amazing collaborators @Bertrand_Charp, @DanielZuegner , and @guennemann!

Monday with @n_gao96 in the reading group "Learning Equivariant Non-Local Electron Density Functionals" arxiv.org/abs/2410.07972 Join us on zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg