AI Paper Atlas

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

Closing the Modality Gap Aligns Group-Wise Semantics

Eleonora Grassucci, Giordano Cicchetti, Emanuele Frasca, Aurelio Uncini, Danilo Comminiello

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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 ATP and centroid uniformity losses to InfoNCE to close the modality gapCLIP (LT) · MSCOCO (2 modal)V-Measure: 12.98 -> 23.63Improved
add ATP and centroid uniformity losses to InfoNCECLIP (LT) · MSCOCO (2 modal)text-image R@1: 74.6 -> 70.3Hurt
add ATP and centroid uniformity losses to InfoNCECLIP (LT) · MSR-VTT (3 modal)V-Measure: 23.3 -> 32.1Improved
add ATP and centroid uniformity losses to InfoNCECLIP (FT) · MSR-VTT (3 modal)text-video R@1: 34.8 -> 32.8Hurt
add the proposed gap-closing lossesCLIP · CIFAR10 (2 modal)V-Measure: 67.0 -> 67.9Improved
add the proposed gap-closing lossesCLIP (LT) · AV-MNIST (3 modal)V-Measure: 77.6 -> 82.7Improved
add the proposed gap-closing lossesCLIP (LT) · MSCOCO captioningCIDEr: 153.2 -> 160.9Improved
add the proposed gap-closing lossesCoMM · MultiBench MOSIaccuracy: 65.91 -> 67.65Improved
add the proposed gap-closing lossesCoMM · MultiBench UR-FUNNYaccuracy: 62.83 -> 63.25Improved
add InfoNCE loss to ATP + CU losses (ablation)gap-closing objective · MSR-VTTT2V R@1: 30.0 -> 35.2Improved
add centroid uniformity (CU) weight lambda2 (ablation)InfoNCE + ATP · CIFAR10V-Measure and R@1: R@1 79.39 -> 86.20, V 61.65 -> 66.64 (lambda1=0, lambda2 0 -> 1)Improved
add ATP weight lambda1 on top of CU (ablation)InfoNCE + CU · CIFAR10V-Measure: 66.64 -> 71.47 (lambda2=1.00, lambda1 0 -> 1.00)Improved

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