# A Generative Foundation Model for Multimodal Histopathology

arXiv: https://arxiv.org/abs/2604.03635 · HTML: https://mlsanity.com/paper/2604.03635/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 72 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection](https://mlsanity.com/paper/2105.10490/) (2021)
- [A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model](https://mlsanity.com/paper/2407.15362/) (2024)
- [PathLDM: Text conditioned Latent Diffusion Model for Histopathology](https://mlsanity.com/paper/2309.00748/) (2023)
- [PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology](https://mlsanity.com/paper/2401.16355/) (2024)
- [Deep Learning-enabled Virtual Histological Staining of Biological Samples](https://mlsanity.com/paper/2211.06822/) (2022)
- [Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs](https://mlsanity.com/paper/2303.06193/) (2023)
- [UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia grading](https://mlsanity.com/paper/2101.09991/) (2021)
- [Predicting Ki67, ER, PR, and HER2 Statuses from H&E-stained Breast Cancer Images](https://mlsanity.com/paper/2308.01982/) (2023)
- [HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology](https://mlsanity.com/paper/2505.12120/) (2025)
- [PixCell: A generative foundation model for digital histopathology images](https://mlsanity.com/paper/2506.05127/) (2025)
- [Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges](https://mlsanity.com/paper/2505.10993/) (2025)
- [GANs vs. Diffusion Models for virtual staining with the HER2match dataset](https://mlsanity.com/paper/2506.18484/) (2025)
- [GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow](https://mlsanity.com/paper/2511.00119/) (2025)

## Built on by (most cited first, 1 of 1)

- [BigCell: Generating Gigapixel Whole-Slide Images](https://mlsanity.com/paper/2610.14261/) (2026)

## Abstract (arXiv)

Accurate diagnosis and treatment of complex diseases require integrating histological, molecular, and clinical data, yet in practice these modalities are often incomplete owing to tissue scarcity, assay cost, and workflow constraints. Existing computational approaches attempt to impute missing modalities from available data but rely on task-specific models trained on narrow, single source-target pairs, limiting their generalizability. Here we introduce MuPD (Multimodal Pathology Diffusion), a generative foundation model that embeds hematoxylin and eosin (H&E)-stained histology, molecular RNA profiles, and clinical text into a shared latent space through a diffusion transformer with decoupled cross-modal attention. Pretrained on 100 million histology image patches, 1.6 million text-histology pairs, and 10.8 million RNA-histology pairs spanning 34 human organs, MuPD supports diverse cross-modal synthesis tasks with minimal or no task-specific fine-tuning. For text-conditioned and image-to-image generation, MuPD synthesizes histologically faithful tissue architectures, reducing Fr'echet inception distance (FID) scores by 50% relative to domain-specific models and improving few-shot classification accuracy by up to 47% through synthetic data augmentation. For RNA-conditioned histology generation, MuPD reduces FID by 23% compared with the next-best method while preserving cell-type distributions across five cancer types. As a virtual stainer, MuPD translates H&E images to immunohistochemistry and multiplex immunofluorescence, improving average marker correlation by 37% over existing approaches. These results demonstrate that a single, unified generative model pretrained across heterogeneous pathology modalities can substantially outperform specialized alternatives, providing a scalable computational framework for multimodal histopathology.