Language Models Can Control Their Own Attention: 52% Less KV Cache Reading

rohanpaul_ai · x · 2026-09-05

The arXiv paper 'Language Models Can Control Their Own Attention' (Namgyu Ho et al.) introduces Declarative Attention (DA): since models attend to only a small fraction of context yet scan the full KV cache each step, DA has the model declare its attention needs in chain-of-thought, splitting generation into <global> (full context), <focus> (a specific region), and <local> (recent output) modes. The inference engine parses these like tool calls and skips most KV cache reads—no external scorer with O(N) per-step cost.

Zero-shot across 15 long-context tasks:

Accuracy loss shrinks with model scale, and the authors frame DA as a new axis of sparse attention with further potential under training-based methods.

Related event: Google paper proposes Declarative Attention, cutting attention cost by 52%(2 posts)→

Original post →

More from Infra

Infra channel →