Research map / Vision-language and multimodal / Cross-modal learning
ProbMED: A Probabilistic Framework for Medical Multimodal Binding
Yuan Gao, Sangwook Kim, Jianzhong You, Chris McIntosh
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 |
|---|---|---|---|
| Hellinger similarity instead of cosine (ablation) | ProbMED probabilistic embeddings · MIMIC-CXR/ECG/ECHO retrieval | RSUM: 260.3 vs 251.4 | Improved |
| CSD similarity instead of cosine (ablation) | ProbMED probabilistic embeddings · MIMIC-CXR/ECG/ECHO retrieval | RSUM: 184.4 vs 251.4 | Hurt |
| Bhattacharyya similarity instead of cosine (ablation) | ProbMED probabilistic embeddings · MIMIC-CXR/ECG/ECHO retrieval | RSUM: 241.1 vs 251.4 | Hurt |
| Add SIS loss (ablation) | Hellinger baseline · MIMIC retrieval | RSUM: 261.3 vs 260.3 | Improved |
| Add BatchNorm before feature aggregation (ablation) | Hellinger baseline · MIMIC retrieval | RSUM: 262.3 vs 260.3 | Improved |
| SIS loss plus BatchNorm together (ablation) | Hellinger baseline · MIMIC retrieval | RSUM: 264.8 vs 260.3 | Improved |
| Uncertainty-based prompt filtering (ablation) | zero-shot CXR classification · CheXchoNet/RSNA/COVID/Montgomery | AUROC SUM: 331.6 vs 326.6 (all 80 prompts) | Improved |
| Feature sampling from learned distributions (n=16) | few-shot classification · few-shot datasets | AUROC | Improved |
| Fusing CXR and ECG (ablation) | ProbMED multimodal classification · MIMIC-CONNECT CKD/CHD | AUROC SUM: 458.6 vs 450.8 (CXR only) | Improved |
Closest papers by meaning
- Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training (ICML 2024 · similarity 0.86)
- MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text (AAAI 2026 · similarity 0.86)
- MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images (CVPR 2026 · similarity 0.86)
- Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation (NeurIPS 2025 · similarity 0.86)
- How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images (ICLR 2026 · similarity 0.86)
- Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE (NeurIPS 2024 · similarity 0.86)
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.
