Spotlight paper proposes growing memory with constant per-token cost, between Attention and linear attention

EugeneVinitsky · x · 2026-10-03

A research thread introduces Spotlight, a new architecture targeting the core long-context memory tradeoff:

A direct answer to the memory-vs-cost dilemma in long-context modeling.

Related event: Percepta Unveils Spotlight: Decoupling Intelligence from Unbounded Memory(7 posts)→

Original post →

More from Infra

Infra channel →