arXiv:2511.11212v1 Announce Type: new 
Abstract: Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Instead of building separate models, we propose MAFM^3 (Modular Adaptation of Foundation Models for Multi-Modal Medical AI), a framework that enables a single foundation model to expand into diverse domains, tasks, and modalities through lightweight modular components. These components serve as specialized skill sets that allow the system to flexibly activate the appropriate capability at the inference time, depending on the input type or clinical objective. Unlike conventional adaptation methods that treat each new task or modality in isolation, MAFM^3 provides a unified and expandable framework for efficient multitask and multimodality adaptation. Empirically, we validate our approach by adapting a chest CT foundation model initially trained for classification into prognosis and segmentation modules. Our results show improved performance on both tasks. Furthermore, by incorporating PET scans, MAFM^3 achieved an improvement in the Dice score 5% compared to the respective baselines. These findings establish that foundation models, when equipped with modular components, are not inherently constrained to their initial training scope but can evolve into multitask, multimodality systems for medical imaging. The code implementation of this work can be found at https://github.com/Areeb2735/CTscan_prognosis_VLM

يقدم المقال MAFM^3، وهو إطار مصمم للتكيف المعياري للنماذج الأساسية في الذكاء الاصطناعي الطبي متعدد الأنماط. يتناول التحدي المتمثل في ندرة البيانات في التصوير الطبي من خلال السماح لنموذج أساسي واحد بالتكيف مع مجالات ومهام وأنماط متنوعة باستخدام مكونات معيارية خفيفة. تتيح هذه الطريقة تفعيلًا مرنًا للقدرات المحددة بناءً على نوع الإدخال أو الهدف السريري، مما يحسن من التكيف متعدد المهام ومتعدد الأنماط.

El artículo presenta MAFM^3, un marco diseñado para la adaptación modular de modelos fundamentales en IA médica multimodal. Aborda el desafío de la escasez de datos en la imagenología médica al permitir que un solo modelo fundamental se adapte a diversos dominios, tareas y modalidades mediante componentes modulares ligeros. Este enfoque permite la activación flexible de capacidades específicas según el tipo de entrada u objetivo clínico, mejorando así la adaptación multitarea y multimodal.

L'article présente MAFM^3, un cadre conçu pour l'adaptation modulaire des modèles fondamentaux dans l'IA médicale multimodale. Il aborde le défi des données limitées en imagerie médicale en permettant à un seul modèle fondamental de s'adapter à divers domaines, tâches et modalités grâce à des composants modulaires légers. Cette approche permet une activation flexible de capacités spécifiques en fonction du type d'entrée ou de l'objectif clinique, améliorant ainsi l'adaptation multitâche et multimodalité.

The article introduces MAFM^3, a framework designed for the modular adaptation of foundation models in multi-modal medical AI. It addresses the challenge of limited data in medical imaging by allowing a single foundation model to adapt to various domains, tasks, and modalities using lightweight modular components. This approach enables flexible activation of specific capabilities based on the input type or clinical objective, improving multitask and multimodality adaptation.

MAFM^3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI

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

MAFM^3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Magicley AI

Octofy

AIPortalX

Zemith-3bda3b

Ready to build your own newsroom?