arXiv:2507.07860v2 Announce Type: replace 
Abstract: Progress in a research field can be hard to assess, in particular when many concurrent methods are proposed in a short period of time. This is the case in digital pathology, where many foundation models have been released recently to serve as feature extractors for tile-level images, being used in a variety of downstream tasks, both for tile- and slide-level problems. Benchmarking available methods then becomes paramount to get a clearer view of the research landscape. In particular, in critical domains such as healthcare, a benchmark should not only focus on evaluating downstream performance, but also provide insights about the main differences between methods, and importantly, further consider uncertainty and robustness to ensure a reliable usage of proposed models. For these reasons, we introduce THUNDER, a tile-level benchmark for digital pathology foundation models, allowing for efficient comparison of many models on diverse datasets with a series of downstream tasks, studying their feature spaces and assessing the robustness and uncertainty of predictions informed by their embeddings. THUNDER is a fast, easy-to-use, dynamic benchmark that can already support a large variety of state-of-the-art foundation, as well as local user-defined models for direct tile-based comparison. In this paper, we provide a comprehensive comparison of 23 foundation models on 16 different datasets covering diverse tasks, feature analysis, and robustness. The code for THUNDER is publicly available at https://github.com/MICS-Lab/thunder.

لقد جعلت التقدمات الأخيرة في علم الأمراض الرقمية، وخاصة مع إدخال نماذج أساسية مختلفة لصور مستوى البلاط، من الضروري تقييم هذه الأساليب. هذه التقييمات مهمة لأنها تساعد الباحثين والممارسين على تقييم فعالية الأساليب المختلفة في مجال يتطور بسرعة. من خلال وضع معايير واضحة، يمكن للمجتمع أن يفهم بشكل أفضل أي الأساليب تعمل بشكل أفضل لمهام محددة، مما يحسن في النهاية دقة التشخيص ونتائج المرضى.

Los recientes avances en patología digital, especialmente con la introducción de varios modelos fundamentales para imágenes a nivel de mosaico, han hecho que sea esencial evaluar estos métodos. Esta evaluación es crucial ya que ayuda a investigadores y profesionales a valorar la efectividad de diferentes enfoques en un campo que evoluciona rápidamente. Al establecer referencias claras, la comunidad puede entender mejor qué métodos funcionan mejor para tareas específicas, mejorando en última instancia la precisión diagnóstica y los resultados para los pacientes.

Les récentes avancées en pathologie numérique, notamment avec l'introduction de divers modèles fondamentaux pour les images au niveau des tuiles, rendent essentiel l'évaluation de ces méthodes. Cette évaluation est cruciale car elle aide les chercheurs et les praticiens à évaluer l'efficacité des différentes approches dans un domaine en évolution rapide. En établissant des références claires, la communauté peut mieux comprendre quelles méthodes fonctionnent le mieux pour des tâches spécifiques, améliorant ainsi la précision diagnostique et les résultats pour les patients.

The recent advancements in digital pathology, particularly with the introduction of various foundation models for tile-level images, have made it essential to benchmark these methods. This benchmarking is crucial as it helps researchers and practitioners assess the effectiveness of different approaches in a rapidly evolving field. By establishing clear benchmarks, the community can better understand which methods work best for specific tasks, ultimately improving diagnostic accuracy and patient outcomes.

THUNDER: Tile-level Histopathology image UNDERstanding benchmark

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

THUNDER: Tile-level Histopathology image UNDERstanding benchmark

Was this article worth reading? Share it

One More Thing in AI

File Architect

ThumbnailPilot

AIPortalX

Attentive AI

THANK JOHN

Ready to build your own newsroom?