AI Paper Atlas

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

CoRiM: Conflict-driven Risk Minimization for Dynamic Multimodal Fusion

Shihao Zou, Wei Wei

CVPR 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
use all three risk terms instead of fused uncertainty only (ablation)CoRiM · MVSA (eps=5, avg)accuracy: 71.87 -> 75.65Improved
use all three risk terms instead of JS consistency only (ablation)CoRiM · MVSA (eps=10, avg)accuracy: 60.50 -> 65.34Improved
use JS divergence instead of symmetric KL (ablation)CoRiM · MVSA (eps=10, avg)accuracy: 63.01 -> 65.34Improved
use JS divergence instead of Hellinger (ablation)CoRiM · MVSA (eps=5, avg)accuracy: 72.29 -> 75.65Improved
use per-sample weights instead of global weights (ablation)CoRiM · MVSA (eps=5, avg)accuracy: 68.54 -> 75.65Improved
use per-sample weights instead of class-level weights (ablation)CoRiM · MVSA (eps=10, avg)accuracy: 64.05 -> 65.34Improved
use Frank-Wolfe instead of projected gradient descent (ablation)CoRiM · MVSA (eps=10, avg)accuracy: 59.99 -> 65.34Improved
use Frank-Wolfe instead of entropic mirror descent (ablation)CoRiM · MVSA (eps=10, avg)accuracy: 61.40 -> 65.34Improved
replace scalar-proxy weighting (PDF) with conflict risk minimizationmultimodal fusion · MVSA (eps=10, avg)accuracy: 63.09 -> 65.34Improved
replace ReconBoost with CoRiM on three-modality datamultimodal fusion · CH-SIMSaccuracy: 73.88 -> 73.68No clear effect
replace ReconBoost with CoRiM on three-modality datamultimodal fusion · MOSEIaccuracy: 68.61 -> 69.21Improved

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