Nishikawa, N., Higuchi, R., & Suzuki, T. (2025). Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency.
Chicago Style (17th ed.) CitationNishikawa, Naoki, Rei Higuchi, and Taiji Suzuki. Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency. 2025.
MLA (9th ed.) CitationNishikawa, Naoki, et al. Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency. 2025.
Warning: These citations may not always be 100% accurate.