Research map / Vision-language and multimodal / Cross-modal learning
InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling
Chenxin Li, Yifan Liu, Panwang Pan, Hengyu Liu, Xinyu Liu, Wuyang Li, Cheng Wang, Weihao Yu, Yiyang Lin, Yixuan Yuan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the conditional cross-modal MI (NCE) objective (ablation) | InfoBridge · CREMA-D | accuracy: 56.81 -> 62.85 | Improved |
| add the protective margin term (ablation) | InfoBridge · CREMA-D | accuracy: 58.52 -> 62.85 | Improved |
| add the protective margin term (ablation) | InfoBridge · GBMLGG | accuracy: 87.79 -> 91.15 | Improved |
| add context-aware prior (condition T) (ablation) | InfoBridge · CREMA-D | accuracy: 60.61 -> 62.85 | Improved |
| use ground-truth semantic categories instead of k=5 clusters as condition T (ablation) | InfoBridge · AVE | accuracy: 67.52 -> 68.19 | Improved |
| use ground-truth semantic categories instead of retrieval-based T (ablation) | InfoBridge · Food-101 | accuracy: 82.66 -> 84.03 | Improved |
| replace InfoNCE with conditional MI plus protective margin | multimodal fusion baseline · GBMLGG | accuracy: 90.67 -> 92.15 | Improved |
| replace InfoNCE with InfoBridge | multimodal fusion · AVE | accuracy: 67.52 -> 68.19 | No clear effect |
| joint training of modalities versus unimodal training | CREMA-D baseline · CREMA-D | accuracy: 54.40 -> 53.20 | Hurt |
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.
- ReconBoost — ReconBoost: Boosting Can Achieve Modality Reconcilement (ICML 2024) · better on 2 of 2 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
- What to align in multimodal contrastive learning? (ICLR 2025 · similarity 0.89)
- Asymmetric Reinforcing Against Multi-Modal Representation Bias (AAAI 2025 · similarity 0.88)
- InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions (NeurIPS 2025 · similarity 0.88)
- MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data (NeurIPS 2026 · similarity 0.88)
- $\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts (ICML 2025 · similarity 0.88)
- SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning (NeurIPS 2026 · similarity 0.87)
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.
