Publications

‍

2026

Float8@2bits: Entropy Coding Enables Data-Free Model Compression (Preprint)

Patrick Putzky, Martin Genzel, Mattes Mollenhauer, Sebastian Schulze, Thomas Wollmann, Stefan Dietzel

‍

2025

Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation.

Martin Genzel, Patrick Putzky, Pengfei Zhao, Sebastian Schulze, Mattes Mollenhauer, Robert Seidel, Stefan Dietzel, Thomas Wollmann

Transactions on Machine Learning Research

‍

Regularized least squares learning with heavy-tailed noise is minimax optimal

Mattes Mollenhauer, Nicole Mücke, Dimitri Meunier, Arthur Gretton

Advances in Neural Information Processing Systems (NeurIPS)

‍

Can automatic rodent behavior analysis using AI/ML contribute to drug safety? Initial insights from DeepRod

B. Weiss, K. Eschmann, C. Weinandi, P. Schwarz, F.-Z. Khamlichi, H. Behnke, M. Garafolj, O. Akhtar, A. Loy, H. Schauerte, T. Wollmann, G. Rast

Toxicology Letters

‍

Robust Weight Imprinting: Insights from Neural Collapse and Proxy-Based Aggregation

Justus Westerhoff, Golzar Atefi, Mario Koddenbrock, Alexei Figueroa, Alexander Löser, Erik Rodner, Felix A. Gers

Transactions on Machine Learning Research

‍

Compressing Large Language Models to Any Size Without Recomputation

Martin Genzel, Patrick Putzky, Pengfei Zhao, Sebastian Schulze, Mattes Mollenhauer, Robert Seidel, Stefan Dietzel, Thomas Wollmann

ICML Workshop ES-FoMo

‍

Deep Joint Source-Channel Coding for Small Satellite Applications.

Olga Kondrateva, Grace Li Zhang, Julian Zobel, Björn Scheuermann, Stefan Dietzel

‍

2024

Squirrel: A Python library that enables ML teams to share, load, and transform data in a collaborative, flexible, and efficient way

Alireza Sohofi, Tiansu Yu, Alp Aribal, Winfried Loetzsch, Thomas Wollmann

‍

Memorization with neural networks: going beyond the worst case

Sjoerd Dirksen, Patrick Finke, Martin Genzel

Journal of Machine Learning Research

‍

Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms

Dimitri Meunier, Zikai Shen, Mattes Mollenhauer, Arthur Gretton, Zhu Li

Advances in Neural Information Processing Systems (NeurIPS)

‍

Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm

Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton

Journal of Machine Learning Research

‍

Adaptable Deep Joint Source-and-Channel Coding for Small Satellite Applications

Olga Kondrateva, Stefan Dietzel, Björn Scheuermann

‍

Quantority: Parameter Prioritization for Incremental Updates of Convolutional Neural Networks in Small Satellite Missions

Olga Kondrateva, Stefan Dietzel, Björn Scheuermann

IFIP Networking Conference

‍

DeepRod: A human-in-the-loop system for automatic rodent behavior analysis

Adrian Loy, Miha Garafolj, Heike Schauerte, Hanna Behnke, Cyrille Charnier, Philipp Schwarz, Georg Rast, Thomas Wollmann

ICML Workshop DMLR

‍

Progressive Updates of Convolutional Neural Networks for Enhanced Reliability in Small Satellite Applications

Olga Kondrateva, Stefan Dietzel, Maximilian Schambach, Johannes Otterbach, Björn Scheuermann

Computer Communications

‍

Explainability and Interpretability in Electric Load Forecasting Using Machine Learning Techniques

Lukas Baur, Konstantin Ditschuneit, Maximilian Schambach, Can Kaymakci, Thomas Wollmann, Alexander Sauer

Energy and AI

‍

Integrating Cloud Computing, Bayesian Optimization, and Neural-Additive Modeling for Enhanced CAM Systems in 5-Axis Milling

Viktor Rudel, Georg Vinogradov, Philipp Ganser, Thomas Bergs, Christopher Vahl, Markus Frings, Valentina König, Maximilian Schambach, Stefan Dietzel, Michael Königs

Procedia CIRP

‍

2023

Multiscale Neural Operators for Solving Time-Independent PDEs

Winfried Ripken, Lisa Coiffard, Felix Pieper, Sebastian Dziadzio

NeurIPS Workshop DLDE

‍

Scaling Experiments in Self-Supervised Cross-Table Representation Learning

Maximilian Schambach, Dominique Paul, Johannes S. Otterbach

NeurIPS Workshop TRL

‍

Towards Tabular Foundation Models - Status Quo, Challenges, and Opportunities

Maximilian Schambach

‍

Self-distilled Representation Learning for Time Series.

Felix Pieper, Konstantin Ditschuneit, Martin Genzel, Alexandra Lindt, Johannes Otterbach

NeurIPS Workshop SSL

‍

Curve Your Enthusiasm: Concurvity Regularization in Differentiable GAMs

Julien Siems, Konstantin Ditschuneit, Winfried Ripken, Alma Lindborg, Maximilian Schambach, Johannes Otterbach, Martin Genzel

Advances in Neural Information Processing Systems (NeurIPS)

‍

Joint source and channel coding for small satellite applications

Olga Kondrateva, Stefan Dietzel, Björn Scheuermann

IEEE Conference on Local Computer Networks (LCN)

‍

Filling the Gap: Fault-Tolerant Updates of On-Satellite Neural Networks Using Vector Quantization

Olga Kondrateva, Stefan Dietzel, Maximilian Schambach, Johannes Otterbach, Björn Scheuermann

IFIP Networking Conference

‍

Parameter Prioritization for Efficient Transmission of Neural Networks in Small Satellite Applications

Olga Kondrateva, Stefan Dietzel, Ansgar Lößer, Björn Scheuermann

Mediterranean Communication and Computer Networking Conference (MedComNet)

‍

Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation

Alexander Koenig, Maximilian Schambach, Johannes S. Otterbach

CVPR Workshop SAIAD

‍

SECREDAS: Safe and (Cyber-) Secure Cooperative and Automated Mobility

Chris van der Ploeg, Jacco van de Sluis, Sebastian Gerres, Szabolcs Novaczki, András Wippelhauser, Eric Nassor, Julien Sevin, András Gazdag, Gergely Biczók

IFAC World Congress

‍

NAM-CAM: Neural-Additive Models for Semi-analytic Descriptions of CAM Simulations

Konstantin Ditschuneit, Adem Frenk, Markus Frings, Viktor Rudel, Stefan Dietzel, Johannes S. Otterbach

‍

Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management

Julien Siems, Maximilian Schambach, Sebastian Schulze, Johannes S. Otterbach

ICLR Workshop AI4ABM

‍

2022

Auto-Compressing Subset Pruning for Semantic Image Segmentation

Konstantin Ditschuneit, Johannes S. Otterbach

Pattern Recognition

‍

Towards Learning Self-Organized Criticality of Rydberg Atoms using Graph Neural Networks

Simon Ohler, Daniel Steven Brady, Winfried Lötzsch, Michael Fleischhauer, Johannes Otterbach

ICML Workshop AI4Science

‍

Scalable Flow Optimization for Small Satellite Networks using Benders Decomposition

Olga Kondrateva, Stefan Dietzel, Björn Scheuermann

IEEE International Symposium on a World of Wireless, Mobile, and Multimedia Networks (WoWMoM)

‍

Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks

Winfried Lötzsch, Simon Ohler, Johannes S. Otterbach

ICML Workshop AI4Science

‍

2021

Chameleon: A semi-automated machine learning framework designed for the rapid and scalable development and deployment of production-ready machine learning systems for small and medium-sized enterprises

Johannes Otterbach, Thomas Wollmann

GI Computer Science

‍

DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

Samuel von Baußnern, Johannes Otterbach, Adrian Loy, Mathieu Salzmann, Thomas Wollmann

‍‍

MEAL: Manifold Embedding-based Active Learning

Deepthi Sreenivasaiah, Johannes Otterbach, Thomas Wollmann

ICCV Workshops

‍