← all papers · overview

Interleaved Head Attention

Abstract

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: attention heads produce exactly independent attention matrices, with no communication between heads during attention computation. This becomes problematic for multi-step reasoning, where correct answers depend

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).