{"type":"link","version":"1.0","title":"Selecting a few high-attention tokens per block as its lookup key beats mean-pooling for retrieving cached attention state","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/block-level-kv-retrieval-with-representative-tokens","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}