Lukas Gosch

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.

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/ @guennemann

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

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. 🧵👇

📣 Our spicy ICML 2025 position paper: “Graph Learning Will Lose Relevance Due To Poor Benchmarks”. Graph learning is less trendy in the ML world than it was in 2020-2022. We believe the problem is in poor benchmarks that hold the field back - and suggest ways to fix it! 🧵1/10

We will present our work “Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen” at #ICLR2025. Meet us tomorrow at 10 am, Hall 3, poster #17! This is joint work with @TillRichter6 hanyi manuel @AlexanderTong7 @andrea_dittadi @fabian_theis

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

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).

📣Announcing VerifAI: AI Verification in the Wild, a workshop at #ICLR2025 VerifAI will gather researchers to explore topics at the intersection of genAI/trustworthyML and verification: verifai-workshop.github.io @celine_ylee @theo_olausson @ameeshsh @wellecks @taoyds

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

📢 We are delighted to reveal the Best Paper Awards: 🏆 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? and 🏆 Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks 👏👏👏

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

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

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!

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!

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

Deep learning with differential privacy can protect sensitive information of individuals. But what about groups of multiple users? We answer this question in our #NeurIPS2024 paper arxiv.org/abs/2403.04867 Joint work w/ @mihail_sto @ArthurK48147 @guennemann. #Neurips (1/7)

11 exciting news: Our group has 10 papers at #NeurIPS2024 (incl. 1 oral + 2 spotlights) 📃🎓. And as of October 1st, I am on entrepreneurial leave 🚀. Re papers: Congrats to all co-authors. Amazing work! go.tum.de/689644 Re startup: We are hiring! pruna.ai

Three papers @NeurIPSConf 2024 🎉 An efficient adv. training algorithm for LLMs arxiv.org/abs/2405.15589 Unlearned LLMs are not safe against adv. attacks arxiv.org/abs/2402.09063 Scaling robustness of Lipschitz-1 networks arxiv.org/abs/2305.10388 Happy to chat in Vancouver!