AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Way Representation Alignment

Akshit Achara, Tatiana Gaintseva, Matéo Mahaut, Pritish Chakraborty, Viktor Stenby Johansson, Melih Barsbey, Emanuele Rodolà, Donato Crisostomi

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 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
apply geometry-corrected alignment (GCPA) on top of GPAGPA · MASSIVE clusteringARI: 0.198 -> 0.300Improved
apply GCPA instead of GCCAGCCA · MASSIVE clusteringNMI: 0.508 -> 0.617Improved
align with GPA instead of no alignmentNA · MASSIVE clusteringARI: 0.198 -> 0.198No clear effect
apply GCPA instead of GCCA, 3 languagesGCCA · TED-Multi (M=3)rank-1 accuracy, worst pair: 0.509 -> 0.532Improved
apply GCPA instead of GCCA, 10 languagesGCCA · TED-Multi (M=10)rank-1 accuracy, worst pair: 0.288 -> 0.314Improved
align with GPA universe instead of pairwise maps, 10 languagesPW · TED-Multi (M=10)rank-1 accuracy, average: 0.430 -> 0.433Improved
add GCPA correction to GPA for multimodal agreementGPA · Flickr8k tripletsmatched cross-modal distance: 0.729 -> 0.560Improved
add GCPA correction to GPAGPA · Flickr8k tripletsGamma90: 0.760 -> 0.853Improved
apply GCPA instead of GCCA under noisy correspondencesGCCA · Flickr30k noisyR@1: 0.607 -> 0.613Improved
add GCPA correction when fragile pair has 50% Canny corruption (ablation)GPA · CIFAR-100 fragile pairprobing accuracy: 0.719 -> 0.643Hurt
add GCPA correction when fragile pair has 75% Canny corruption (ablation)GPA · CIFAR-100 fragile pairprobing accuracy: 0.670 -> 0.568Hurt
add new model with GPA-ADD instead of refitting universe (ablation)GPA-REFIT · CIFAR-100 continual additionmean difference from refitting: -0.002No clear effect

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