AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Faster Query-Key Learning Sharpens Attention in Self-Attention Models

Rahul Vashisht, Harish G. Ramaswamy

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 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 faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · SQuAD QA (6-layer GPT)test performance: 56.11 -> 56.86No clear effect
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · SQuAD QA (6-layer GPT)attention confidence (AC): 12.65 -> 42.95Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · SQuAD QA (6-layer GPT)sufficiency (lower better): 0.69 -> 0.59Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · SQuAD QA (6-layer GPT)comprehensiveness: 0.38 -> 0.53Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · Subject-verb agreement (1-layer)test performance: 92.434 -> 93.412No clear effect
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · Subject-verb agreement (1-layer)attention confidence (AC): 41.67 -> 76.85Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · Subject-verb agreement (1-layer)sufficiency (lower better): 0.24 -> 0.15Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · Subject-verb agreement (1-layer)comprehensiveness: 0.24 -> 0.30Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · HateXplain (1-layer)test performance: 55.74 -> 56.90No clear effect
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · HateXplain (1-layer)attention confidence (AC): 0.00 -> 43.5Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · HateXplain (1-layer)sufficiency (lower better): 0.41 -> 0.32Improved
add faster query-key learning rate (ablation)single/multi-layer self-attention, AdamW · HateXplain (1-layer)comprehensiveness: 0.40 -> 0.48Improved

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