Wiedemer, Thaddäus

12 publications

ICLR 2025 In Search of Forgotten Domain Generalization Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

ICLRW 2025 In Search of Forgotten Domain Generalization Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

ICML 2025 LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel

ICLRW 2025 LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel

ICCV 2025 VGGSounder: Audio-Visual Evaluations for Foundation Models Daniil Zverev, Thaddäus Wiedemer, Ameya Prabhu, Matthias Bethge, Wieland Brendel, A. Sophia Koepke

ICLR 2024 Does CLIP’s Generalization Performance Mainly Stem from High Train-Test Similarity? Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

ICMLW 2024 In Search of Forgotten Domain Generalization Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

NeurIPSW 2024 Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks Thaddäus Wiedemer, Yash Sharma, Ameya Prabhu, Matthias Bethge, Wieland Brendel

ICLR 2024 Provable Compositional Generalization for Object-Centric Learning Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel

NeurIPS 2023 Compositional Generalization from First Principles Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel

NeurIPSW 2023 Does CLIP’s Generalization Performance Mainly Stem from High Train-Test Similarity? Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

CVPRW 2022 Few-Shot Supervised Prototype Alignment for Pedestrian Detection on Fisheye Images Thaddäus Wiedemer, Stefan Wolf, Arne Schumann, Kaisheng Ma, Jürgen Beyerer