AI Paper Atlas

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

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

Chengxuan Qian, Shuo Xing, Li Li, Yue Zhao, Zhengzhong Tu

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 heterogeneity alignment (ablation)DecAlign · CMU-MOSIF1 Score: 84.03 -> 85.82Improved
add homogeneity alignment (ablation)DecAlign · CMU-MOSIF1 Score: 84.46 -> 85.82Improved
add heterogeneity alignment (ablation)DecAlign · CMU-MOSEIMAE: 0.588 -> 0.543Improved
add feature decoupling (MFD) (ablation)DecAlign · CMU-MOSIF1 Score: 81.56 -> 81.92Improved
add prototype-guided optimal transport (ablation)DecAlign · CMU-MOSIF1 Score: 84.17 -> 85.82Improved
add prototype-guided optimal transport (ablation)DecAlign · CMU-MOSEIMAE: 0.624 -> 0.543Improved
add cross-modal transformer (ablation)DecAlign · CMU-MOSIF1 Score: 84.36 -> 85.82Improved
add semantic consistency loss (ablation)DecAlign · CMU-MOSIF1 Score: 84.73 -> 85.82Improved
add MMD regularization (ablation)DecAlign · CMU-MOSIF1 Score: 84.61 -> 85.82Improved
add MMD regularization (ablation)DecAlign · CMU-MOSEIMAE: 0.564 -> 0.543Improved
use DecAlign instead of DMDDecAlign · CMU-MOSIAcc-2: 83.24 -> 85.75Improved
use DecAlign instead of CGGMDecAlign · IEMOCAP (six-class)WAcc: 72.25 -> 73.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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