AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences

Wenbo Wu, Qingyi Si, Xiurui Pan, Ye Wang, Jie Zhang

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: KV cache eviction and compression

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
retrieve at adaptive semantic boundaries instead of every decoding step (system optimization SR) (ablation)LouisKV · Qwen3-8B, 32K+16Kspeedup: nearly 2.6x speedupImproved
add group-consistent selection (ablation)LouisKV · Qwen3-8B, 32K+16Kspeedup: +13.1%Improved
add custom retrieval CUDA kernel (ablation)LouisKV · Qwen3-8B, 32K+16Kspeedup: +15.7%Improved
use adaptive-stride retrieval instead of fixed-stride retrieval (ablation)LouisKV · LongBench and long-output reasoning tasksaccuracyImproved
use fine-grained clusters/segments instead of page-level management (ablation)LouisKV · LongBench and long-output reasoning tasksaccuracyImproved
raise similarity threshold tau (more frequent retrieval) (ablation)LouisKV · long-input and long-output tasksaccuracy and latencyMixed
use LouisKV instead of Arkvale at budget 512 on long-input tasksLlama-3.1-8B-Instruct · LongBenchaverage accuracy: +1.1% over Arkvale, +3.3% over QuestImproved
use LouisKV instead of Arkvale at budget 1024 on long-output tasksQwen3-8B · long-output reasoningaverage accuracy: +2.0% over Arkvale, +4.8% over QuestImproved
use KV dropping (H2O, RaaS) instead of KV retrievalLlama-3.1-8B-Instruct · LongBench budget 512accuracy: Qasper 44.38 -> 24.50 (H2O)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy