Story
arxiv_cs_cl · Oct 30, 2026 · paper
Source brief
DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
arxiv.orgOct 30, 2026
original source linked
In brief
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is shaped jointly by gat...
Feed lens
eval