Simon Geisler
@geislersi.bsky.social
Interests: machine learning, algorithms, coding
Current: Machine Learning PhD Student at TU Munich with Prof. Stephan Günnemann
Past: @deep-mind.bsky.social, Bosch Center for Artificial Intelligence, Bosch Connected Services
Current: Machine Learning PhD Student at TU Munich with Prof. Stephan Günnemann
Past: @deep-mind.bsky.social, Bosch Center for Artificial Intelligence, Bosch Connected Services
Pinned
Simon Geisler
@geislersi.bsky.social
· Feb 27
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 Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
By Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
Reposted by Simon Geisler
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...
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
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...
Learn more at our #ICML poster: Thu 11am E-2409
Paper: openreview.net/forum?id=U8G...
Code: github.com/martenlienen...
Reposted by Simon Geisler
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
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
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
arxiv.org/abs/2504.06087
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 Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
By Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
February 27, 2025 at 3:16 PM
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 Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
By Günnemann's lab @ TU Munich's lab & Google Research, w/ CAIS support
Here's how we did it. 🧵
Reposted by Simon Geisler
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
Joint work w/ Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar & Stephan Günnemann
L: arxiv.org/pdf/2407.10867
December 14, 2024 at 5:14 PM
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
Joint work w/ Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar & Stephan Günnemann
L: arxiv.org/pdf/2407.10867
Reposted by Simon Geisler
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!
🗣️ 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
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!
🗣️ 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!