AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Towards Uniformity and Alignment for Multimodal Representation Learning

Wenzhe Yin, Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Stratis Gavves

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 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 tuple-level uniformity U(C) (ablation)UniAlign · MSR-VTT ablationavg Recall@1: 36.6 -> 38.6Improved
add tuple-level alignment L_vol (ablation)UniAlign · MSR-VTT ablationavg Recall@1: 36.6 -> 37.6Improved
add both U(C) and L_vol (ablation)UniAlign · MSR-VTT ablationavg Recall@1: 36.6 -> 41.8Improved
add L_vol on top of U(C) (ablation)UniAlign · MSR-VTT ablationavg Recall@1: 38.6 -> 41.8Improved
add tuple-level losses U(C) and L_vol (ablation)UniAlign · Zero-shot retrieval averageT2V Recall@1: 57.4 -> 58.8Improved
add tuple-level losses U(C) and L_vol (ablation)UniAlign · DiDeMo zero-shotV2T Recall@1: 51.9 -> 51.6Hurt
change centroid temperature from 0.01 to 0.07 (ablation)UniAlign · MSR-VTTavg Recall@1: 55.2 -> 55.3No clear effect
increase lambda_align from 0.5 to 1.5 (ablation)UniAlign basic instantiation · MSR-VTT (from scratch)avg Recall@1: 27.8 -> 19.45Hurt
increase lambda_align from 0.2 to 0.5 (ablation)UniAlign basic instantiation · MSR-VTT (from scratch)avg Recall@1: 25.3 -> 27.8Improved
replace GRAM with UniAlignGRAM · Zero-shot retrievalT2V Recall@1: +3.0 R@1 on T2V and 1.6 on V2TImproved
replace VAST with UniAlign from same pretrained weightsVAST · Zero-shot retrievalRecall@1: 8.7 R@1 on T2V and 6.4 R@1 on V2TImproved
replace GRAM with UniAlign (Euclidean)GRAM · VGGSound generation (Kandinsky)FID: 87.23 -> 46.60Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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