Shirin Reyhanian, M.Sc.

RUB
FOR2812
People
Shirin Reyhanian, M.Sc.

shirin.reyhanian@ini.rub.de

NB 3/70

https://www.ini.rub.de/the_institute/people/shirin-reyhanian/

Publications

2026

Is Hierarchical Quantization Essential for Optimal Reconstruction?
Reyhanian, S., & Wiskott, L.
In Proceedings of the 15th International Conference on Pattern Recognition Applications and Methods (pp. 671–679) SCITEPRESS - Science and Technology Publications

@inproceedings{ReyhanianWiskott2026, author = {Reyhanian, Shirin and Wiskott, Laurenz}, title = {Is Hierarchical Quantization Essential for Optimal Reconstruction?}, booktitle = {Proceedings of the 15th International Conference on Pattern Recognition Applications and Methods}, pages = {671–679}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2026}, doi = {10.5220/0014648500004067}, }

Reyhanian, S., & Wiskott, L.. (2026). Is Hierarchical Quantization Essential for Optimal Reconstruction? In Proceedings of the 15th International Conference on Pattern Recognition Applications and Methods (pp. 671–679). SCITEPRESS - Science and Technology Publications. http://doi.org/10.5220/0014648500004067

2025

Understanding Transformer-based Vision Models through Inversion
Rathjens, J., Reyhanian, S., Kappel, D., & Wiskott, L.

@misc{RathjensReyhanianKappelEtAl2025, author = {Rathjens, Jan and Reyhanian, Shirin and Kappel, David and Wiskott, Laurenz}, title = {Understanding Transformer-based Vision Models through Inversion}, year = {2025}, }

Rathjens, J., Reyhanian, S., Kappel, D., & Wiskott, L.. (2025). Understanding Transformer-based Vision Models through Inversion. Retrieved from https://arxiv.org/abs/2412.06534

2024

Analysis of a Generative Model of Episodic Memory Based on Hierarchical VQ-VAE and Transformer
Reyhanian, S., Fayyaz, Z., & Wiskott, L.
In Proceedings of the 33rd International Conference on Artificial Neural Networks (ICANN 2024), Lugano, Switzerland Springer Nature Switzerland

link

@inproceedings{ReyhanianFayyazWiskott2024, author = {Reyhanian, Shirin and Fayyaz, Zahra and Wiskott, Laurenz}, title = {Analysis of a Generative Model of Episodic Memory Based on Hierarchical VQ-VAE and Transformer}, booktitle = {Proceedings of the 33rd International Conference on Artificial Neural Networks (ICANN 2024), Lugano, Switzerland}, publisher = {Springer Nature Switzerland}, month = {September}, year = {2024}, doi = {10.1007/978-3-031-72341-4_6}, }

Reyhanian, S., Fayyaz, Z., & Wiskott, L.. (2024). Analysis of a Generative Model of Episodic Memory Based on Hierarchical VQ-VAE and Transformer. In Proceedings of the 33rd International Conference on Artificial Neural Networks (ICANN 2024), Lugano, Switzerland. Springer Nature Switzerland. http://doi.org/10.1007/978-3-031-72341-4_6

The research unit FOR 2812 "Constructing scenarios of the past: A new framework in episodic memory" is a project funded by the German Research Foundation (Deutsche Forschungsgemeinschaft, DFG). The research unit studies the cognitive and neuronal mechanisms underlying scenario construction in episodic memory. We employ and integrate approaches from Philosophy, Psychology, and Experimental and Computational Neuroscience.

Contact

Universitätsstr. 150,
44801 Bochum, Germany

Tel: +49 (0)234 32 27996
Fax: +49 (0)234 32 14210