Prasanna Mayilvahanan

According to our database, Prasanna Mayilvahanan authored at least 7 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery.

Jana Zeller, Thaddäus Wiedemer, Fanfei Li, Thomas Klein, Prasanna Mayilvahanan, Matthias Bethge, Felix A. Wichmann, Ryan Cotterell, Wieland Brendel

CoRR, February, 2026

2025

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model.

Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thaddäus Wiedemer, Wieland Brendel

CoRR, October, 2025

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws.

Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel

Proceedings of the Forty-second International Conference on Machine Learning, 2025

In Search of Forgotten Domain Generalization.

Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

Proceedings of the Proceedings on "I Can't Believe It's Not Better: Challenges in Applied Deep Learning" at ICLR 2025 Workshops, 2025

2024

Does CLIP's generalization performance mainly stem from high train-test similarity?

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Compositional Generalization from First Principles.

Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Representation Learning for the Clustering of Multi-Omics Data.

Gautier Viaud, Prasanna Mayilvahanan, Paul-Henry Cournède

IEEE ACM Trans. Comput. Biol. Bioinform., 2022