Sara Dragutinovic

According to our database, Sara Dragutinovic authored at least 2 papers in 2025.

Collaborative distances:

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

2025

Softmax ≥ Linear: Transformers may learn to classify in-context by kernel gradient descent.

Sara Dragutinovic, Andrew M. Saxe, Aaditya K. Singh

CoRR, October, 2025

Strategy Coopetition Explains the Emergence and Transience of In-Context Learning.

Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe

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