Timur Carstensen

According to our database, Timur Carstensen authored at least 8 papers in 2025.

Collaborative distances:

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

2025

Selective Rotary Position Embedding.

Sajad Movahedi, Timur Carstensen, Arshia Afzal, Frank Hutter, Antonio Orvieto, Volkan Cevher

CoRR, November, 2025

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting.

Vladyslav Moroshan, Julien Siems, Arber Zela, Timur Carstensen, Frank Hutter

CoRR, October, 2025

Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation.

Arjun Krishnakumar, Rhea Sanjay Sukthanker, Hannan Javed Mahadik, Gabriela Kadlecová, Vladyslav Moroshan, Timur Carstensen, Frank Hutter, Aaron Klein

CoRR, October, 2025

Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison.

Marianna Nezhurina, Jörg K. H. Franke, Taishi Nakamura, Timur Carstensen, Niccolò Ajroldi, Ville Komulainen, David Salinas, Jenia Jitsev

CoRR, September, 2025

Quickly Tuning Foundation Models for Image Segmentation.

Breenda Das, Lennart Purucker, Timur Carstensen, Frank Hutter

CoRR, August, 2025

DeltaProduct: Increasing the Expressivity of DeltaNet Through Products of Householders.

Julien Siems, Timur Carstensen, Arber Zela, Frank Hutter, Massimiliano Pontil, Riccardo Grazzi

CoRR, February, 2025

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products.

Julien Siems, Timur Carstensen, Arber Zela, Frank Hutter, Massimiliano Pontil, Riccardo Grazzi

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization.

Timur Carstensen, Neeratyoy Mallik, Frank Hutter, Martin Rapp

Proceedings of the International Conference on Automated Machine Learning (AutoML 2025), 2025