works on
counter-causal attention 1inference optimization 1kv cache management 1large language models 1memory efficiency 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Back from the Future: Key-Value Cache Management by Counter-Causal Surprise

Stephen Gould, Anton van den Hengel

The paper introduces a KV cache eviction method for large language models that removes entries predicted well by future tokens using a counter‑causal attention pass, improving memo…