Random Attention
Random Attention is Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning — keep the prompt, evict the rest at random. Accuracy matches learned evictors; serving is 32–43% faster.. It is ranked #2557 on the AI Radar, in AI research, first seen 14 days ago and shared in 1 post (1.1k views).
Random Attention Random Attention Rethinking KV Cache Eviction for Efficient Reasoning Heng Wang 1,2 , Jielin Qiu 1 , Wenting Zhao 1 , Cheng Qian 1,2 , Liangwei Yang 1 , Jiawei Han 2 , Heng Ji 2 , Silvio Savarese 1 , Shelby Heinecke 1 , Huan Wang 1 1 Salesforce AI Research · 2 University of Illinois Urbana-Champaign 📄 arXiv ⭐ Code 🤗 HF Paper Thread BibTeX TL;DR — Every KV cache eviction method scores cached tokens and keeps the top-K. We drop the score entirely: keep the prompt, evict the rest uniformly at random within each attention head. Across four reasoning models and six tasks, it matches the strongest prior evictor — and is…
Alternatives to Random Attention
- academy.dair.ai — Chat with Paper
- alphaXiv — Now on @askalphaxiv
- flashprove — Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that…
- moe-blogpost — A hands-on guide to training Mixture-of-Experts models
- liberai.com — Technical blog
- Science's Last Exam — Can AI do research, end to end? Science's Last Exam defines and measures whether an AI agent can carry a research goal…
Random Attention in numbers
- Rank on the AI Radar: #2557 of 10402
- Shared in 1 post by 1 account: @qingke_ai
- 1.1k views on those posts
- First seen 14 days ago, last shared 14 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: AI research
FAQ
What is Random Attention?
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning — keep the prompt, evict the rest at random. Accuracy matches learned evictors; serving is 32–43% faster. It was first shared on X 14 days ago and is ranked #2557 on the AI Radar.
Is Random Attention free?
Pricing is not stated on the page we read.
Who shared Random Attention?
1 account on X, including @qingke_ai, in 1 post totalling 1.1k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.