mlsanityData to 7 Oct 2026

Atlas 2 -- Foundation models for clinical deployment

arXiv 2601.05148 ↗First posted 8 Jan 2026cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Pathology foundation models substantially advanced the possibilities in computational pathology --- yet tradeoffs in terms of performance, robustness, and computational requirements remained, which limited their clinical deployment. In this report, we present Atlas 2, Atlas 2-B, and Atlas 2-S, three pathology vision foundation models which bridge these shortcomings by showing state-of-the-art prediction performance, robustness, and resource efficiency in a comprehensive evaluation across eighty public benchmarks. Our models were trained on the largest pathology foundation model dataset to date comprising 5.5 million histopathology whole slide images, collected from three medical institutions Charit'e - Universit"atsmedizin Berlin, LMU Munich, and Mayo Clinic.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 30 of its 68 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

30 of 68 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  6. 2018Rotation Equivariant CNNs for Digital Pathologycited by 420
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  8. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  9. 2024Multimodal Whole Slide Foundation Model for Pathologycited by 156
  10. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 148
  11. 2024HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysiscited by 104
  12. 2024PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathologycited by 80
18 more
  1. 2024Phikon-v2, A large and public feature extractor for biomarker predictioncited by 67
  2. 2021A Petri Dish for Histopathology Image Analysiscited by 63
  3. 2024A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Modelcited by 59
  4. 2024Hibou: A Family of Foundational Vision Transformers for Pathologycited by 52
  5. 2024RudolfV: A Foundation Model by Pathologists for Pathologistscited by 40
  6. 2025Current Pathology Foundation Models are unrobust to Medical Center Differencescited by 37
  7. 2024CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathologycited by 34
  8. 2025Distilling foundation models for robust and efficient models in digital pathologycited by 33
  9. 2024The Clever Hans Effect in Unsupervised Learningcited by 24
  10. 2025Training state-of-the-art pathology foundation models with orders of magnitude less datacited by 19
  11. 2024PLUTO: Pathology-Universal Transformercited by 17
  12. 2024Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Studycited by 17
  13. 2024Unsupervised Foundation Model-Agnostic Slide-Level Representation Learningcited by 15
  14. 2024AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnosticscited by 8
  15. 2024Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shiftscited by 8
  16. 2022Evaluating histopathology transfer learning with ChampKitcited by 7
  17. 2025Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Losscited by 7
  18. 2025MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classificationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathologycited by 2
  2. 2026OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGAcited by 2
  3. 2026Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracycited by 0
  4. 2026Robustifying pathology foundation models via fine-tuningcited by 0
  5. 2026Morphology signal in whole slide image foundation models can automatically triage slidescited by 0
  6. 2026HERO: Histology Encoder for Robust Representation in Oncologycited by 0