Tobias Christian Nauen

16 papers A 1B 1Journal 13Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors.
Trans. Mach. Learn. Res.
Brian Bernhard Moser, Shalini Sarode, Federico Raue, Stanislav Frolov, Krzysztof Adamkiewicz, Arundhati S. Shanbhag, Joachim Folz, Tobias Christian Nauen, Andreas Dengel
2026 J jnl
When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators.
CoRR
Krzysztof Adamkiewicz, Brian B. Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel
2025 J jnl
A Study in Dataset Distillation for Image Super-Resolution.
CoRR
Tobias Dietz, Brian B. Moser, Tobias Christian Nauen, Federico Raue, Stanislav Frolov, Andreas Dengel
2025 B conf
Distill the Best, Ignore the Rest: A Study in Latent Dataset Distillation on Core-Sets.
IJCNN
Brian B. Moser, Federico Raue, Tobias Christian Nauen, Stanislav Frolov, Andreas Dengel
2025 J jnl
ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation.
CoRR
Tobias Christian Nauen, Brian B. Moser, Federico Raue, Stanislav Frolov, Andreas Dengel
2025 J jnl
HyperCore: Coreset Selection under Noise via Hypersphere Models.
CoRR
Brian B. Moser, Arundhati S. Shanbhag, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Joachim Folz, Andreas Dengel
2025 J jnl
PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors.
CoRR
Brian B. Moser, Shalini Sarode, Federico Raue, Stanislav Frolov, Krzysztof Adamkiewicz, Arundhati S. Shanbhag, Joachim Folz, Tobias Christian Nauen, Andreas Dengel
2025 J jnl
SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection.
CoRR
Brian B. Moser, Tobias Christian Nauen, Arundhati S. Shanbhag, Federico Raue, Stanislav Frolov, Joachim Folz, Andreas Dengel
2025 A conf
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers.
WACV
Tobias Christian Nauen, Sebastian Palacio, Federico Raue, Andreas Dengel
2024 J jnl
A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift.
CoRR
Sanath Budakegowdanadoddi Nagaraju, Brian B. Moser, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel
2024 J jnl
Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning.
CoRR
Brian B. Moser, Federico Raue, Tobias Christian Nauen, Stanislav Frolov, Andreas Dengel
2024 J jnl
Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning.
CoRR
Arundhati S. Shanbhag, Brian B. Moser, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel
2024 J jnl
TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax.
CoRR
Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
2024 — conf
TaylorShift: Shifting the Complexity of Self-attention from Squared to Linear (and Back) Using Taylor-Softmax.
ICPR (6)
Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
2024 J jnl
Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution.
CoRR
Brian B. Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel
2023 J jnl
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers.
CoRR
Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel