Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces

Bond, Andrew, Özlü, Ege Erdem, Çimen, Tuna, Melanlioglu, Ilkin Umut, Birdal, Tolga, Erdem, Erkut, Erdem, Aykut

Open source

DOI
10.48550/arxiv.2609.27988
Published
2026
Container
Not recorded
Publisher
arXiv
Open access
yes

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.48550/arxiv.2609.27988,
  title = {Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces},
  author = {Bond, Andrew and Özlü, Ege Erdem and Çimen, Tuna and Melanlioglu, Ilkin Umut and Birdal, Tolga and Erdem, Erkut and Erdem, Aykut},
  year = {2026},
  doi = {10.48550/arxiv.2609.27988},
  url = {https://doi.org/10.48550/arxiv.2609.27988}
}

RIS

TY  - JOUR
TI  - Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
AU  - Bond, Andrew
AU  - Özlü, Ege Erdem
AU  - Çimen, Tuna
AU  - Melanlioglu, Ilkin Umut
AU  - Birdal, Tolga
AU  - Erdem, Erkut
AU  - Erdem, Aykut
PY  - 2026
DO  - 10.48550/arxiv.2609.27988
UR  - https://doi.org/10.48550/arxiv.2609.27988
ER  - 

APA

Andrew, B., Erdem, Ö. E., Tuna, Ç., Umut, M. I., Tolga, B., Erkut, E., & Aykut, E. (2026). Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces. https://doi.org/10.48550/arxiv.2609.27988

Source records