AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity

Viet-Hoang Tran, Khanh Vinh Bui, Van-Hoan Trinh, Tan Lai Ngoc, Tan Minh Nguyen

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Attention head mechanisms · 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 Stage 2 (orthogonal alignment) on top of Stage 1 head permutation (ablation)weight matching for attention · CIFAR-10 / CIFAR-100 / IMDB / DBPedia, APE and RoPEloss barrier ratio (%): 78.3 -> 10.2 (CIFAR-10 APE)Improved
add gradient descent fine-tuning to Stage 2 orthogonal initialization (ablation)weight matching for attention · CIFAR-10 / CIFAR-100 / IMDB / DBPedia, APE and RoPEloss barrier ratio (%): 10-16% -> 7-12%Improved
add gradient descent to Stage 2 (Variant 2 to full) (ablation)weight matching for attention · CIFAR-10 (APE)loss barrier ratio (%): 10.2 -> 8.7Improved
add gradient descent to Stage 2 (Variant 2 to full) (ablation)weight matching for attention · IMDB reviews (APE)accuracy barrier ratio (%): 15.3 -> 10.1Improved
use Stage 1 head permutation matching vs best of 24 permutationsweight matching for attention · CIFAR-10 (APE)rank out of 24 (loss): 2.40No clear effect
re-initialize the entire Transformer on large-scale benchmarksattention LMC · ImageNet, WikiText-103, Enwik8, One Billion Wordlinear mode connectivityHurt
re-initialize only the first attention layerattention LMC · vision and text benchmarkslinear mode connectivityImproved

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