AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Training-Free Hashing-Based Attention via Binary Principal Components

Daohai Yu, Zhanpeng Zeng, Keyu Chen, Wenhao Li, Zhifeng Shen, Luxi Lin, Ruizhi Qiao, Xing Sun, Rongrong Ji

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: KV cache eviction and compression · 0 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 error-aware safeguard (EAS) at 2% budget (ablation)BinaryPC (online projection) · InfiniteBench (Llama-3.1-8B)average score: 41.30 -> 47.42Improved
add EAS to BinaryPC with offline calibration (ablation)BinaryPC w/ OPC · InfiniteBench (Llama-3.1-8B)average score: 46.93 -> 47.34Improved
increase EAS budget from 2% to 15% (ablation)BinaryPC · InfiniteBench (Llama-3.1-8B)average score: 47.42 to 47.63No clear effect
add offline projection calibration (OPC)BinaryPC · Short-context LM-Eval (Llama-3-8B)average accuracy: 59.31 -> 63.82Improved
increase hash length from 32 to 64 bits (ablation)BinaryPC · NIAH (Llama-3.1-8B)average score: 86.37 -> 90.18Improved
increase hash length from 64 to 128 bits (ablation)BinaryPC · NIAH (Llama-3.1-8B)no clear effect: 90.18 -> 90.00No clear effect
calibrate OPC on PG19 only instead of mixed corpora (ablation)BinaryPC w/ OPC · LongBenchaverage score: 30.39 -> 30.43No clear effect
use data-aware binary principal components instead of random LSH projectionshashing-based sparse attention · RULER average (Llama-3.1-8B)average score: 84.68 -> 85.57Improved
use 1K token budget instead of 2% (ablation)BinaryPC · LongBench (Llama-3.1-8B)average score: 49.50 -> 49.66Improved
use 2K budget instead of 2% on RULER (ablation)BinaryPC · RULER average (Llama-3.1-8B)average score: 85.57 -> 87.06Improved

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