APA (7th ed.) Citation

Dragutinović, S., Saxe, A. M., & Singh, A. K. (2025). Softmax $\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent.

Chicago Style (17th ed.) Citation

Dragutinović, Sara, Andrew M. Saxe, and Aaditya K. Singh. Softmax $\geq$ Linear: Transformers May Learn to Classify In-context by Kernel Gradient Descent. 2025.

MLA (9th ed.) Citation

Dragutinović, Sara, et al. Softmax $\geq$ Linear: Transformers May Learn to Classify In-context by Kernel Gradient Descent. 2025.