Research map / Vision-language and multimodal / Cross-modal learning
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
Divyam Madaan, Sumit Chopra, Kyunghyun Cho
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 |
|---|---|---|---|
| include the time-series modality in MIMIC-III mortality prediction | unimodal baseline · MIMIC-III mortality | accuracy (%): 76.36 -> 77.89 | Improved |
| add the time-series modality for respiratory ICD-9 460-519 prediction | unimodal baseline · MIMIC-III ICD-9 460-519 | accuracy (%): 56.22 -> 68.22 | Improved |
| add the time-series modality for neoplasm ICD-9 140-239 prediction | unimodal baseline · MIMIC-III ICD-9 140-239 | accuracy (%): 91.42 -> 91.37 | No clear effect |
| add the audio modality on AV-MNIST | unimodal vision baseline · AV-MNIST | accuracy (%): 40.36 -> 71.32 | Improved |
| PRIMO latent completion with complete modalities versus the multimodal baseline | PRIMO · AV-MNIST | accuracy (%): 71.14 -> 68.17 (audio), 71.32 -> 68.27 (vision) | Hurt |
| use PRIMO versus MVAE and MMVAE with complete inputs on XOR | missing-modality models · Synthetic XOR | accuracy | Improved |
Closest papers by meaning
- Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness (NeurIPS 2026 · similarity 0.91)
- Mitigating Pervasive Modality Absence Through Multimodal Generalization and Refinement (AAAI 2025 · similarity 0.90)
- Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning (NeurIPS 2024 · similarity 0.89)
- Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models (NeurIPS 2026 · similarity 0.88)
- MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data (NeurIPS 2026 · similarity 0.88)
- Knowledge Bridger: Towards Training-Free Missing Modality Completion (CVPR 2025 · similarity 0.88)
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.
