Lukas Gosch
lukasgosch.bsky.social
Lukas Gosch
@lukasgosch.bsky.social
Researcher. Optimization. Graph ML. PhD Student @TU Munich, DAML. relAI Fellow. Quirk for Philosphy. He/Him
Reposted by Lukas Gosch
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.

Learn more at our #ICML poster: Thu 11am E-2409

Paper: openreview.net/forum?id=U8G...
Code: github.com/martenlienen...
July 14, 2025 at 3:56 PM
Excited to announce our #ICLR2025 spotlight work deriving the first exact certificates for neural networks against label poisoning 🎉. Joint work with @maha-saba.bsky.social, Stephan Günnemann & Debarghya Ghoshdastidar. For details, check out the thread below👇 or our paper arxiv.org/abs/2412.00537.
May 5, 2025 at 3:05 PM
Reposted by Lukas Gosch
I am truly excited to share our latest work with @mscherbela.bsky.social, Philipp Grohs, and @guennemann on "Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems"!

arxiv.org/abs/2504.06087
Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems
We present finite-range embeddings (FiRE), a novel wave function ansatz for accurate large-scale ab-initio electronic structure calculations. Compared to contemporary neural-network wave functions, Fi...
arxiv.org
April 9, 2025 at 9:30 AM
Super happy & honored that our work on certifying NNs against poisoning won the Best Paper Award at AdvML-Frontiers@ #NeurIPS2024. Come by our poster 10:40am-12&4-5pm (or talk) today :)

Joint work w/ Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar & Stephan Günnemann

L: arxiv.org/pdf/2407.10867
December 14, 2024 at 5:14 PM
Reposted by Lukas Gosch
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=HRk...

Happy to chat!
December 9, 2024 at 5:23 PM