Berestizshevsky, K., Andri, R., & Cavigelli, L. (2025). Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding.
Chicago Style (17th ed.) CitationBerestizshevsky, Konstantin, Renzo Andri, and Lukas Cavigelli. Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding. 2025.
MLA (9th ed.) CitationBerestizshevsky, Konstantin, et al. Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding. 2025.
Warning: These citations may not always be 100% accurate.