LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
机构 * University of Southern California(南加州大学) ; Intel Labs(英特尔实验室) ; Amazon AGI(亚马逊人工智能实验室) ; Case Western Reserve University(凯斯西储大学)
Comments 17 pages, 8 figures. EMNLP2025 Findings