Apollo builds unified multimodal temporal patient embeddings from 25 billion records across 28 modalities and demonstrates forecasting on 322 prognosis and retrieval tasks including 5-year disease onset prediction.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 4roles
baseline 1polarities
baseline 1representative citing papers
MuPD is a pretrained generative foundation model using a diffusion transformer with cross-modal attention that synthesizes histopathology images from text or RNA data and outperforms task-specific models on generation, augmentation, and virtual staining tasks.
An automated curation pipeline extracts 11M high-fidelity medical image-text pairs from PMC, yielding CLIP and MLLM vision encoders that outperform baselines on 26 benchmarks and a clinical dermatology retrieval task.
GazeX uses radiologist gaze trajectories as a behavioral prior during pretraining to generate more accurate and expert-consistent results in chest X-ray report generation, disease grounding, and visual question answering.
citing papers explorer
-
A multimodal and temporal foundation model for virtual patient representations at healthcare system scale
Apollo builds unified multimodal temporal patient embeddings from 25 billion records across 28 modalities and demonstrates forecasting on 322 prognosis and retrieval tasks including 5-year disease onset prediction.
-
A Generative Foundation Model for Multimodal Histopathology
MuPD is a pretrained generative foundation model using a diffusion transformer with cross-modal attention that synthesizes histopathology images from text or RNA data and outperforms task-specific models on generation, augmentation, and virtual staining tasks.
-
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models
An automated curation pipeline extracts 11M high-fidelity medical image-text pairs from PMC, yielding CLIP and MLLM vision encoders that outperform baselines on 26 benchmarks and a clinical dermatology retrieval task.
-
Seeing Through Experts Eyes A Foundational Vision Language Model Trained on Radiologists Gaze and Reasoning
GazeX uses radiologist gaze trajectories as a behavioral prior during pretraining to generate more accurate and expert-consistent results in chest X-ray report generation, disease grounding, and visual question answering.