HOLA: Adding Hippocampus-like Precise Memory to Linear Attention

omarsar0 · x · 2026-07-03

A new paper proposes HOLA: adding a bounded exact KV memory module on top of the compressed recurrent states of linear attention or state space models, acting as a "hippocampal" supplement. Linear attention compresses the entire context into a fixed-size state to achieve O(1) memory, but early facts get overwritten and needle recall degrades when numerous key-value associations compete. HOLA restores long-term memory capabilities without sacrificing the efficiency of linear attention.

Original post →

More from Research

Research channel →