APA (7th ed.) Citation

Yan, F., Nguyen, H., Akbarian, P., Ho, N., & Rinaldo, A. (2025). Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective.

Chicago Style (17th ed.) Citation

Yan, Fanqi, Huy Nguyen, Pedram Akbarian, Nhat Ho, and Alessandro Rinaldo. Sigmoid Self-Attention Has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective. 2025.

MLA (9th ed.) Citation

Yan, Fanqi, et al. Sigmoid Self-Attention Has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective. 2025.