Publications

Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos (2025). Video Models Are Zero-Shot Learners and Reasoners.

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

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

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

Prasanna Mayilvahanan, Roland S Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel (2024). In Search of Forgotten Domain Generalization. ICLR 2025 (Spotlight).

Mark Basting, Robert-Jan Bruintjes, Thaddäus Wiedemer, Matthias Kümmerer, Matthias Bethge, Jan Van Gemert (2024). Scale Learning in Scale-Equivariant Convolutional Networks. VISAPP 2024.

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel (2023). Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?. ICLR 2024.

Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel (2023). Provable Compositional Generalization for Object-Centric Learning. ICLR 2024 (Oral).

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

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