Max Lübbering

Max Lübbering

Auto-generated profile, based on publicly available information

Max Lübbering

Fraunhofer IAIS

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 July 2022 in International Journal of Data Science and Analytics
Verified
Journal Article
Open access
PDF file
MLMax Lübbering
Max Lübbering
MGMichael Gebauer
Michael Gebauer
RRRajkumar Ramamurthy
Rajkumar Ramamurthy
CBChristian Bauckhage
Christian Bauckhage
RSRafet Sifa
Rafet Sifa
One-vs-Rest (OVR) classification aims to distinguish a single class of interest (COI) from other classes. The concept of novelty detection and robustness to dataset shift becomes crucial in OVR when the scope of the rest class is extended from the classes observed during training to unseen and possibly unrelated classes, a setting referred to as open set recognition (OSR). In this work, we propose a novel architecture, namely decoupling autoencoder (DAE), which provides a proven upper bound on the open space risk and minimizes open space risk via a dedicated training routine. Our method is benchmarked within three different scenarios, each isolating different aspects of OSR, namely plain classification, outlier detection, and dataset shift. The results conclusively show that DAE achieves robust performance across all three tasks. This level of cross-task robustness is not observed for any of the seven potent baselines from the OSR, OVR, outlier detection, and ensembling domain which, apart from ATA (Lübbering et al., From imbalanced classification to supervised outlier detection problems: adversarially trained auto encoders. In: Artificial neural networks and machine learning—ICANN 2020, 2020), tend to fail on either one of the tasks. Similar to DAE, ATA is based on autoencoders and facilitates the reconstruction error to predict the inlierness of a sample. However unlike DAE, it does not provide any uncertainty scores and therefore lacks rudimentary means of interpretation. Our adversarial robustness and local stability results further support DAE’s superiority in the OSR setting, emphasizing its applicability in safety-critical systems.

14 October 2020
Verified
Book Chapter
Closed access
PDF file
MLMax Lübbering
Max Lübbering
RRRajkumar Ramamurthy
Rajkumar Ramamurthy
MGMichael Gebauer
Michael Gebauer
TBThiago Bell
Thiago Bell
RSRafet Sifa
Rafet Sifa
CBChristian Bauckhage
Christian Bauckhage

30 September 2021
Verified
Book Chapter
Closed access
PDF file
MBMarius Bulla
Marius Bulla
LHLars Hillebrand
Lars Hillebrand
MLMax Lübbering
Max Lübbering
RSRafet Sifa
Rafet Sifa

18 August 2020
Verified
Book Chapter
Closed access
PDF file
RARhys Agombar
Rhys Agombar
MLMax Luebbering
Max Luebbering
RSRafet Sifa
Rafet Sifa

23 February 2021
Verified
Book Chapter
Closed access
PDF file
MLMax Lübbering
Max Lübbering
MGMichael Gebauer
Michael Gebauer
RRRajkumar Ramamurthy
Rajkumar Ramamurthy
RSRafet Sifa
Rafet Sifa
CBChristian Bauckhage
Christian Bauckhage

9 February 2026 in arXiv
Verified
Preprint
Open access
PDF file
MLMax Lübbering
Max Lübbering
TRTimm Ruland
Timm Ruland
RRRichard Rutmann
Richard Rutmann
FSFelix Stollenwerk
Felix Stollenwerk
DFDavid Fitzek
David Fitzek
MAMehdi Ali
Mehdi Ali
Today's LLM (pre-) training and research workflows typically allocate a significant amount of compute to large-scale ablation studies. Despite the substantial compute costs of these ablations, existing open-source frameworks provide limited tooling for these experiments, often forcing researchers to write their own wrappers and scripts. We propose Modalities, an end-to-end PyTorch-native framework that integrates data-driven LLM research with large-scale model training from two angles. Firstly, by integrating state-of-the-art parallelization strategies, it enables both efficient pretraining and systematic ablations at trillion-token and billion-parameter scale. Secondly, Modalities adopts modular design with declarative, self-contained configuration, enabling reproducibility and extensibility levels that are difficult to achieve out-of-the-box with existing LLM training frameworks.