Tobias Christian Nauen

Tobias Christian Nauen

PhD Student

RPTU University Kaiserslautern-Landau

German Research Center for Artificial Intelligence (DFKI)

About Me

Iā€™m a researcher of artificial intelligence at DFKI and RPTU Kaiserslautern-Landau. My research interests include efficient deep learning, transformer models, multimodal learning, and computer vision. In my PhD project, my focus lies on the development of efficient transformer models for vision, language, and multimodal tasks.

Education

  • M.Sc. in Mathematics , Leibniz University Hannover (2022)
  • B.Sc. in Computer Science , Leibniz University Hannover (2022)
  • B.Sc. in Mathematics , Leibniz University Hannover (2019)

Interests

Artificial Intelligence Computer Vision Efficient Transformer Models
Skills
Technical
Python
Linux Terminal
LaTeX
Hobbies
šŸŽø Electric Guitar
šŸ„¾ Hiking
šŸš² Bicycle Traveling
Featured Publications
ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation featured image
Deep Learning

ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation

arXiv
We improve the training of vision transformers by segmenting and recombining objects and backgrounds from datasets. This makes the transformers more accurate, as well as more robust.
avatar
Tobias Christian Nauen
PDF Code Dataset Supplementary Material
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers featured image
Deep Learning

Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers

WACV 2025
A comprehensive benchmark and analysis of more than 45 transformer models for image classification to evaluate their efficiency, considering various performance metrics. We find the optimal architectures to use and uncover that model-scaling is more efficient than image scaling.
avatar
Tobias Christian Nauen
PDF Code Poster Slides Data Explorer Supplementary Material
Recent Publications
Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel (2026). When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators. arXiv.
PDF
Brian Bernhard Moser, Shalini Sarode, Federico Raue, Krzysztof Adamkiewicz, Arundhati Shanbhag, Joachim Folz, Tobias Christian Nauen, Andreas Dengel (2025). PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors. arXiv.
PDF
Brian Bernhard Moser, Arundhati Shanbhag, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Joachim Folz, Andreas Dengel (2025). HyperCore: Coreset Selection under Noise via Hypersphere Models. arXiv.
PDF
Brian Bernhard Moser, Tobias Christian Nauen, Arundhati Shanbhag, Federico Raue, Stanislav Frolov, Joachim Folz, Andreas Dengel (2025). SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection. arXiv.
PDF
Brian B. Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel (2025). When 512Ɨ512 is not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution. ICIP 2025.
PDF Code DOI
See all publications ā†’
Tools & Software
AI Deadlines Tracker featured image
AI

AI Deadlines Tracker

An open-source tracker of AI and machine learning conference deadlines, featuring advanced filtering by rating, h5-index, and timeline. Designed to help researchers plan submissions efficiently across 90+ venues.
AI Deadlines Code
Research Projects
Albatross logo
Albatross

At its core, Albatross is a research project in the area of continual learning.

SustAInML logo
SustAInML

SustainML is dedicated to creating a sustainable ML framework for Green AI. By prioritizing energy efficiency, SustainML aims to pave the way for environmentally conscious AI solutions that are both efficient and effective.

Sustainable Embedded AI logo
Sustainable Embedded AI

Energy- and data-saving methods for environmental perception in embedded AI systems using the case study of smart factory and smart farming applications; funded by the Carl Zeiss Foundation.

Contact

Office

Office 3.09

Trippstadter Str. 122

67663 Kaiserslautern, Germany

Connect

Email

tobias_christian.nauen@dfki.de

Find me on