August 19, 2025Scaled-Dot-Product Attention as One-Sided Entropic Optimal Transport从最优传输的角度理解和统一 Attention 机理NoteAttentionSinkhorn DistanceOptimal TransportationTheory2025
April 1, 2025A Self-Attentive Model for Knowledge TracingSAKT, 自注意力知识追踪NoteKnowledge TracingAttentionEmpiricalEDM2019