AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 23 citations (OpenAlex)

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
add 4-bit quantization on top of Scissorhands at 2x compression (ablation)Scissorhands OPT-6B · Hellaswagaccuracy: 0.706 -> 0.704No clear effect
add 4-bit quantization on top of Scissorhands at 2x compression (ablation)Scissorhands OPT-13B · Hellaswagaccuracy: 0.720 -> 0.720No clear effect
apply Scissorhands KV cache compression (2x) vs original modelOPT-6B · Hellaswagaccuracy: 0.702 -> 0.706No clear effect

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