# Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction

arXiv: https://arxiv.org/abs/2605.08276 · HTML: https://mlsanity.com/paper/2605.08276/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 28 of 28)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [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)
- [Open-vocabulary Object Segmentation with Diffusion Models](https://mlsanity.com/paper/2301.05221/) (2023)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [Methods for Segmentation and Classification of Digital Microscopy Tissue Images](https://mlsanity.com/paper/1810.13230/) (2018)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images](https://mlsanity.com/paper/2004.03037/) (2020)
- [Towards Large-Scale Training of Pathology Foundation Models](https://mlsanity.com/paper/2404.15217/) (2024)
- [Training state-of-the-art pathology foundation models with orders of magnitude less data](https://mlsanity.com/paper/2504.05186/) (2025)
- [HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology](https://mlsanity.com/paper/2505.12120/) (2025)
- [Masked Diffusion as Self-supervised Representation Learner](https://mlsanity.com/paper/2308.05695/) (2023)
- [Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2409.11664/) (2024)
- [PathOrchestra: A Comprehensive Foundation Model for Computational Pathology with Over 100 Diverse Clinical-Grade Tasks](https://mlsanity.com/paper/2503.24345/) (2025)
- [Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology](https://mlsanity.com/paper/2505.21928/) (2025)
- [VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology](https://mlsanity.com/paper/2601.16451/) (2026)
- [nnMIL: A generalizable multiple instance learning framework for computational pathology](https://mlsanity.com/paper/2511.14907/) (2025)

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

- [ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification](https://mlsanity.com/paper/2607.08162/) (2026)

## Abstract (arXiv)

Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely on patch tokenization, which can disrupt spatial continuity and weaken local morphological details needed for cell-level prediction. To address this, we propose Masked-Diffusion Convolutional Foundation Models, termed ConvNeXt Masked-Diffusion (CMD), a self-supervised convolutional generative pretraining framework for dense pathology representation learning. CMD uses a fully convolutional ConvNeXt-UNet backbone, performs masked-diffusion pretraining in pixel space, and incorporates frozen pathology foundation model features through adaptive normalization. Experimental results demonstrate that CMD consistently outperforms existing ViT-based pathology foundation models and even surpasses state-of-the-art end-to-end segmentation methods while fine-tuning only a small number of task-specific parameters across multiple pathology dense prediction tasks. The advantage is particularly pronounced under limited annotation settings, where CMD exhibits stronger robustness and generalization ability. Our findings suggest that purely convolutional architectures can also serve as competitive pathology foundation models for cell-level dense prediction, achieving leading performance within the current ViT-dominated paradigm and providing a scalable, high-performance solution that better preserves histological structural priors for fine-grained pathology understanding.