arXiv:2509.15482v2 Announce Type: replace 
Abstract: Foundation models are increasingly developed in computational pathology (CPath) given their promise in facilitating many downstream tasks. While recent studies have evaluated task performance across models, less is known about the structure and variability of their learned representations. Here, we systematically analyze the representational spaces of six CPath foundation models using techniques popularized in computational neuroscience. The models analyzed span vision-language contrastive learning (CONCH, PLIP, KEEP) and self-distillation (UNI (v2), Virchow (v2), Prov-GigaPath) approaches. Through representational similarity analysis using H&E image patches from TCGA, we find that UNI2 and Virchow2 have the most distinct representational structures, whereas Prov-Gigapath has the highest average similarity across models. Having the same training paradigm (vision-only vs. vision-language) did not guarantee higher representational similarity. The representations of all models showed a high slide-dependence, but relatively low disease-dependence. Stain normalization decreased slide-dependence for all models by a range of 5.5% (CONCH) to 20.5% (PLIP). In terms of intrinsic dimensionality, vision-language models demonstrated relatively compact representations, compared to the more distributed representations of vision-only models. These findings highlight opportunities to improve robustness to slide-specific features, inform model ensembling strategies, and provide insights into how training paradigms shape model representations. Our framework is extendable across medical imaging domains, where probing the internal representations of foundation models can support their effective development and deployment.

أحرزت دراسة حديثة تقدمًا كبيرًا في فهم النماذج الأساسية في علم الأمراض الحاسوبي من خلال تحليل مساحات تمثيلها. هذه الأبحاث مهمة لأنها توضح كيف تتعلم هذه النماذج وتمثل البيانات، مما يمكن أن يعزز تطبيقها في مهام طبية متنوعة. من خلال استخدام تقنيات من علوم الأعصاب الحاسوبية، توفر الدراسة رؤى قد تؤدي إلى تحسين أداء النماذج وتحقيق نتائج أفضل في الرعاية الصحية.

Un estudio reciente ha logrado avances significativos en la comprensión de los modelos fundamentales en patología computacional al analizar sus espacios de representación. Esta investigación es crucial, ya que arroja luz sobre cómo estos modelos aprenden y representan datos, lo que puede mejorar su aplicación en diversas tareas médicas. Al emplear técnicas de neurociencia computacional, el estudio proporciona información que podría llevar a un mejor rendimiento de los modelos y mejores resultados en el cuidado de la salud.

Une étude récente a fait des avancées significatives dans la compréhension des modèles fondamentaux en pathologie computationnelle en analysant leurs espaces de représentation. Cette recherche est cruciale car elle éclaire la manière dont ces modèles apprennent et représentent les données, ce qui peut améliorer leur application dans diverses tâches médicales. En utilisant des techniques de neurosciences computationnelles, l'étude fournit des informations qui pourraient conduire à de meilleures performances des modèles et à de meilleurs résultats en matière de santé.

A recent study has made significant strides in understanding foundation models in computational pathology by analyzing their representational spaces. This research is crucial as it sheds light on how these models learn and represent data, which can enhance their application in various medical tasks. By employing techniques from computational neuroscience, the study provides insights that could lead to improved model performance and better outcomes in healthcare.

Comparing Computational Pathology Foundation Models using Representational Similarity Analysis

arXiv:2601.07944v1 Announce Type: new 
Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex and large-scale predictive problems. The recent success of deep neural networks and foundation models has now given rise to a new paradigm in statistical modeling, in which Bayesian inference can be amortized through large-scale learned predictors. In amortized inference, substantial computation is invested upfront to train a neural network that can subsequently produce approximate posterior or predictions at negligible marginal cost across a wide range of tasks. At deployment, amortized inference offers substantial computational savings compared with traditional Bayesian procedures, which generally require repeated likelihood evaluations or Monte Carlo simulations for predictions for each new dataset.
  Despite the growing popularity of amortized inference, its statistical interpretation and its role within Bayesian inference remain poorly understood. This paper presents statistical perspectives on the working principles of several major neural architectures, including feedforward networks, Deep Sets, and Transformers, and examines how these architectures naturally support amortized Bayesian inference. We discuss how these models perform structured approximation and probabilistic reasoning in ways that yield controlled generalization error across a wide range of deployment scenarios, and how these properties can be harnessed for Bayesian computation. Through simulation studies, we evaluate the accuracy, robustness, and uncertainty quantification of amortized inference under varying signal-to-noise ratios and distributional shifts, highlighting both its strengths and its limitations.

أظهرت دراسة حديثة فعالية الاستدلال المدعوم في الإحصاءات البايزية، خاصة تحت تغيرات نسبة الإشارة إلى الضوضاء وتحولات التوزيع. تستخدم هذه الطريقة الشبكات العصبية العميقة لتبسيط عملية الاستدلال، مما يسمح بتوفير كبير في الحوسبة مقارنة بالأساليب البايزية التقليدية التي تتطلب تقييمات واسعة لاحتمالية.

Un estudio reciente ha evaluado la efectividad de la inferencia amortizada en estadísticas bayesianas, particularmente bajo variaciones en la relación señal-ruido y cambios en la distribución. Este método aprovecha redes neuronales profundas para agilizar el proceso de inferencia, permitiendo ahorros computacionales significativos en comparación con los enfoques bayesianos tradicionales que requieren evaluaciones extensas de verosimilitud.

Une étude récente a évalué l'efficacité de l'inférence amortie dans les statistiques bayésiennes, en particulier sous des variations de rapport signal-bruit et des changements de distribution. Cette méthode utilise des réseaux de neurones profonds pour rationaliser le processus d'inférence, permettant des économies computationnelles significatives par rapport aux approches bayésiennes traditionnelles qui nécessitent des évaluations de vraisemblance étendues.

A recent study has assessed the effectiveness of amortized inference in Bayesian statistics, particularly under varying signal-to-noise ratios and distribution shifts. This method leverages deep neural networks to streamline the inference process, allowing for significant computational savings compared to traditional Bayesian approaches that require extensive likelihood evaluations.

A Statistical Assessment of Amortized Inference Under Signal-to-Noise Variation and Distribution Shift

One More Thing in AI – Your Shortcut to AI Mastery

Comparing Computational Pathology Foundation Models using Representational Similarity Analysis

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

AIPortalX

Octofy

ModelsLab

Https

Ready to build your own newsroom?