Research map / Vision-language and multimodal / Cross-modal learning
Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| dynamically gate features and modalities using feature sparsity and estimated true-class probability | Multimodal classification · BRCA | ACC: 84.2±0.5 -> 87.7±0.3 | Helped |
| dynamically gate features and modalities using feature sparsity and estimated true-class probability | Multimodal classification · LGG | ACC: 81.9±0.8 -> 83.3±1.0 | Helped |
| dynamically gate features and modalities using feature sparsity and estimated true-class probability | Multimodal classification · ROSMAP | ACC: 82.5±0.9 -> 84.2±1.3 | Helped |
| dynamically gate features and modalities using feature sparsity and estimated true-class probability | Multimodal classification · KIPAN | ACC: 99.9±0.2 vs 99.9±0.2 | No clear effect |
| add sparse feature informativeness fusion (ablation) | CF multimodal fusion · BRCA | ACC: 81.5±0.8 -> 84.9±0.6 | Helped |
| add modality informativeness fusion (ablation) | CF multimodal fusion · BRCA | ACC: 81.5±0.8 -> 86.9±0.9 | Helped |
| add both feature and modality informativeness fusion (ablation) | CF multimodal fusion · BRCA | ACC: 81.5±0.8 -> 87.7±0.3 | Helped |
| add sparse feature informativeness fusion (ablation) | CF multimodal fusion · KIPAN | ACC: 99.2±0.5 -> 99.8±0.2 | Helped |
| add modality informativeness fusion (ablation) | CF multimodal fusion · KIPAN | ACC: 99.2±0.5 -> 99.5±0.3 | Helped |
| add both feature and modality informativeness fusion (ablation) | CF multimodal fusion · KIPAN | ACC: 99.2±0.5 -> 99.9±0.2 | Helped |
| add sparse feature informativeness fusion (ablation) | CF multimodal fusion · LGG | ACC: 81.1±1.2 -> 82.4±1.4 | Helped |
| add modality informativeness fusion (ablation) | CF multimodal fusion · LGG | ACC: 81.1±1.2 -> 82.9±0.8 | Helped |
Closest papers by meaning
- Facilitating Multimodal Classification via Dynamically Learning Modality Gap (NeurIPS 2024 · similarity 0.87)
- Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing (ICML 2025 · similarity 0.86)
- Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion (NeurIPS 2025 · similarity 0.86)
- HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data (NeurIPS 2024 · similarity 0.86)
- Semi-Supervised Multimodal Classification Through Learning from Modal and Strategic Complementarities (AAAI 2025 · similarity 0.85)
- Beyond Modality Fusion: Deep Ensembles for Multimodal Classification (NeurIPS 2026 · similarity 0.85)
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.