Maximilian Müller

PhD student, Eberhard-Karls-Universität Tübingen

Joined

September 2022

Names

Maximilian Müller (Preferred)

Maximilian Mueller

Emails

****@wsii.uni-tuebingen.de (Confirmed)

****@barcelonagse.eu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

Eberhard-Karls-Universität Tübingen (uni-tuebingen.de)

2021 – Present

Advisors, Relations & Conflicts

PhD Advisor

Matthias Hein

2021 – 2024

Expertise

No areas of expertise listed

Publications

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein
- Submitted to ICLR 2026
- Readers: Everyone
Unlearning That Lasts: Utility-Preserving, Robust, and almost Irreversible Forgetting in LLMs
Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein
- CCFM Poster
- Readers: Everyone
Mahalanobis++: Improving OOD Detection via Feature Normalization
Maximilian Müller, Matthias Hein
- ICML 2025 poster
- Readers: Everyone
LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion
Maximilian Müller, Matthias Hein
- OpenReview Archive Direct Upload
- Readers: Everyone
How to train your VIT for OOD detection
Maximilian Müller, Matthias Hein
- ICLR 2024 R2-FM Workshop Poster
- Readers: Everyone
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Maximilian Mueller, Tiffany Joyce Vlaar, David Rolnick, Matthias Hein
- NeurIPS 2023 poster
- Readers: Everyone
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
Julian Bitterwolf, Maximilian Mueller, Matthias Hein
- Published: 16 Apr 2023, Last Modified: 15 Feb 2026
- RTML Workshop 2023
- Readers: Everyone
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
Julian Bitterwolf, Maximilian Mueller, Matthias Hein
- Published: 04 Mar 2023, Last Modified: 08 Feb 2026
- ICLR 2023 Workshop on Trustworthy ML Poster
- Readers: Everyone
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
Julian Bitterwolf, Maximilian Müller, Matthias Hein
- ICML 2023 Poster
- Readers: Everyone
A Modern Look at the Relationship between Sharpness and Generalization
Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion
- ICML 2023 Poster
- Readers: Everyone

View all 14 publications