Teresa Dorszewski

According to our database, Teresa Dorszewski authored at least 6 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training.

Kristoffer Wickstrøm, Teresa Dorszewski, Siyan Chen, Michael Kampffmeyer, Elisabeth Wetzer, Robert Jenssen

CoRR, December, 2025

Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models.

Suaiba Amina Salahuddin, Teresa Dorszewski, Marit Almenning Martiniussen, Tone Hovda, Antonio Portaluri, Solveig Thrun, Michael Kampffmeyer, Elisabeth Wetzer, Kristoffer Wickstrøm, Robert Jenssen

CoRR, September, 2025

From Colors to Classes: Emergence of Concepts in Vision Transformers.

Teresa Dorszewski, Lenka Tetková, Robert Jenssen, Lars Kai Hansen, Kristoffer Knutsen Wickstrøm

Proceedings of the Explainable Artificial Intelligence, 2025

Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks.

Teresa Dorszewski, Lenka Tetková, Lorenz Linhardt, Lars Kai Hansen

Proceedings of the Northern Lights Deep Learning Conference, 2025

How Redundant Is the Transformer Stack in Speech Representation Models?

Teresa Dorszewski, Albert Kjøller Jacobsen, Lenka Tetková, Lars Kai Hansen

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Convexity Based Pruning of Speech Representation Models.

Teresa Dorszewski, Lenka Tetková, Lars Kai Hansen

Proceedings of the 34th IEEE International Workshop on Machine Learning for Signal Processing, 2024