AI Paper Atlas

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

Plug, Play, and Fortify: A Low-Cost Module for Robust Multimodal Image Understanding Models

Siqi Lu, Wanying XU, Yongbin Zheng, Wenting Luan, Peng Sun, Jianhang Yao

ICLR 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 MWAMRFNet · BRATS2020average Dice: 85.41 -> 86.41Improved
add MWAMGSS · BRATS2020average Dice: 86.41 -> 87.56Improved
add MWAMmmFormer (ViT-based) · BRATS2020average Dice: 85.64 -> 86.30Improved
add MWAMESANet-MD · NYU-Depth V2average MIoU: 42.53 -> 44.47Improved
add MWAMMMANet · NYU-Depth V2average MIoU: 43.47 -> 45.81Improved
add MWAMSF-MD · CASIA-SURFaverage accuracy: 92.85 -> 96.41Improved
add MWAMMMANet · CASIA-SURFaverage accuracy: 96.06 -> 97.03Improved
add MWAMMMANet · CASIA-SURF, full RGB+Depth+IR inputaccuracy: 99.13 -> 98.74Hurt
add MWAMRFNet · BRATS2020, Flair+T1+T1cDice: 89.36 -> 89.84 Dice; PCR 0.87 -> 1.01Mixed
loss-level intervention only (vs none) (ablation)MWAM on SF-MD · CASIA-SURF averageaccuracy: 92.85 -> 95.06Improved
gradient-level instead of loss-level intervention (ablation)MWAM on SF-MD · CASIA-SURF averageaccuracy: 95.06 -> 95.73Improved
hybrid loss+gradient instead of gradient only (ablation)MWAM on SF-MD · CASIA-SURF averageaccuracy: 95.73 -> 96.41Improved

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