AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Björn Deiseroth, Mayukh Deb, Samuel Weinbach, Manuel Brack, Patrick Schramowski, Kristian Kersting

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Transformer block and depth design · 16 citations (OpenAlex)

Read the paper

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
use AtMan attention-manipulation instead of Chefer gradient methodGPT-J · SQuADmAP: 72.7 -> 73.7Improved
use AtMan instead of CheferGPT-J · SQuADmAR: 96.6 -> 93.4Hurt
use AtMan instead of CheferMAGMA-6B · OpenImagesmAP: 58.3 -> 65.5Improved
use AtMan instead of CheferMAGMA-6B · OpenImagesmAR: 11.7 -> 15.7Improved
add cosine-similarity correlated token suppression (ablation)AtMan · OpenImagesprecision/recallImproved
scale MAGMA from 6B to 13B/30BAtMan · OpenImagesexplanation qualityMixed
apply AtMan to BLIP image encoderAtMan · OpenImagesexplanation qualityNo clear effect
use AtMan instead of gradient methods for memoryTransformers · GPU memorymemory consumptionImproved
use AtMan instead of Chefer for runtimeMAGMA · explaining imageruntimeHurt

Later papers that compared with this method

1 later accepted paper reports AtMan as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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