Chen, Y., Lin, Z., & Yao, Q. (2026). Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers.
Citazione stile Chigago Style (17a edizione)Chen, Yihong, Zhouchen Lin, e Quanming Yao. Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers. 2026.
Citatione MLA (9a ed.)Chen, Yihong, et al. Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers. 2026.
Attenzione: Queste citazioni potrebbero non essere precise al 100%.