Foundation Models for Course Equivalency Evaluation

Introduction: Characterizing the immune contexture is key to understanding the tumor microenvironment, developing biomarkers, and guiding therapeutic strategies. In our previous work on colorectal cancer (CRC), we used a pathologist-guided approach to annotate/count eosinophils and lymphocytes. Their abundance and spatial relationships with tumor cells revealed prognostic significance. While clinically valuable, identifying this demands significant pathologist effort. Advancements in AI, particularly foundational models trained on millions of histology images, have driven significant progress in digital pathology and hold promise to address this gap. However, their application to single-cell tasks remains underexplored. This study investigates the potential of foundation model and compares it with conventional convolutional neural network (CNN) using previously annotated eosinophils and lymphocytes in CRC histology images. Methods: We used 578 CRC cases in The Cancer Genome Atlas with H&E-stained whole-slide images (WSIs) containing 8, 836, 393 cells, including 896, 322 lymphocytes and eosinophils. For evaluation, 109 WSIs were held out as a test set, with 5 WSIs per density quartile selected from our previous study. The foundational model UNI (11.2M parameters) was fine-tuned and a ResNet18 (303M parameters) model was trained. Performance was evaluated using F1-score and AUROC, with Spearman’s correlation accessing WSI-level cell density correlations. Results: For eosinophil, ResNet18 achieved an F1-score of 0.841, AUROC of 0.986, and Spearman's correlation of 0.679, compared to UNI’s 0.847, 0.990, and 0.697, respectively. For lymphocytes, ResNet18 scored 0.697, 0.932, and 0.686, while UNI achieved 0.719, 0.941, and 0.662. ResNet18 performed comparably to UNI despite simpler architecture, at both cell and patient levels. Predicted cell densities generally aligned with the annotated quartiles from previous work, particularly in the 1st and 4th quartiles. Moderate density correlations (0.66-0.69) were observed, but a pathologist's review of misclassified cells revealed imperfections in the semi-supervised cell annotations. Conclusion: The H&E-based AI model for predicting immune cells offers a scalable alternative to manual annotation, enabling automated quantification of existing immune biomarkers like tumor-infiltrating lymphocytes and tumor-associated tissue eosinophilia. Adaptable to other tumor types, it also opens opportunities to discover novel spatial immune biomarkers by leveraging large H&E cohorts and integrating protein-stained immune cell data with histopathological knowledge. Future work will focus on enhancing performance through weakly supervised approaches using carefully selected training cells, and multi-cell type modeling to better capture the morphological characteristics of diverse cell types in a single model. Citation Format: Colwyn Jia Kang Lai, Wei Kit Tan, Marcia Zhang, Timothy Wang, Felicia Wee, Ai Lin Wang, Solomonraj Wilson, Tomotaka Ugai, Joe Sheng Yeong Poh, Jonathan A. Nowak, Shuji Ogino, Juha P. Väyrynen, Mai Chan Lau. Predictive performance comparison of foundational and CNN models for single-cell immune profiling [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 6316.

Introduction: Tumor single-cell data provide unique insights into the cellular dynamics of cancer progression and therapeutic outcomes. Inspired by advancements in natural language processing (NLP), foundation models are increasingly used in single-cell analyses to uncover biological insights and identify clinical biomarkers. However, the performance of these models on cancer-specific tasks remains underexplored. We present an extensive evaluation of foundation models trained on millions of single-cell profiles for cancer-focused investigations. Methods: We evaluated nine predictive models-three traditional methods and six foundation models (four Geneformer and two scGPT models), across various downstream tasks. Traditional models used embeddings from high variable genes (HVG), principal components (PCA), and generative model embedding (scVI), each paired with a random forest classifier for downstream classification. The evaluated foundation models varied in architecture sizes, pretraining dataset sizes (30M to 95M cell profiles), and training datasets, which were either generic or cancer-specific. We assessed the quality of representations by measuring their predictive performance on lung cancer treatment status (TKI treated vs. treatment-naive patients) and breast cancer subtypes (ER+ vs. TNBC). We examined how model characteristics influenced their performance in these domains for all tasks. Results: Zero-shot evaluations of the foundation models showed superior single-cell data clustering, measured by average silhouette width (ASW), compared to traditional methods (HVG, PCA, scVI), suggesting that pre-trained embeddings from millions of single-cell profiles may offer enhanced representations. We thus evaluated the learned representation on downstream predictive tasks, showing that foundation models with a larger pretraining dataset (95M cells), cancer-specific training, larger input size (4096 genes), and deeper model (12 layers) achieved the best performance among foundation models (F1=0.97) for predicting treatment status in lung cancer. In contrast, smaller and generic foundation models had significantly lower performance, however, additional self-supervised training on task-specific data rescued their performance to match larger foundation models. Similar trends were observed in predicting breast cancer subtypes. Notably, the best foundation model’s performance was not significantly different from the best traditional method (PCA) in predicting breast cancer subtypes. Conclusions: These results highlight key factors driving foundation model performance on cancer-specific tasks. While current foundation models show inconsistent contributions to cancer-specific questions, observed performance trends highlight their potential to enhance single-cell data representation and drive significant advancements in cancer research and precision medicine. Citation Format: Haitham Elmarakeby, Ahmed Roman, Shreya Johri, Eliezer M. Van Allen. Evaluation of single-cell foundation models for cancer outcome predictions [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 5084.

Remote sensing (RS) techniques are increasingly crucial for deepening our understanding of the planet. As the volume and diversity of RS data continue to grow exponentially, there is an urgent need for advanced data modeling and understanding capabilities to manage and interpret these vast datasets effectively. Foundation models present significant new growth opportunities and immense potential to revolutionize the RS field. In this paper, we conduct a comprehensive technical survey on foundation models in RS, offering a brand-new perspective by exploring their evolution from unimodality to multimodality. We hope this work serves as a valuable entry point for researchers interested in both foundation models and RS and helps them launch new projects or explore new research topics in this rapidly evolving area. This survey addresses the following three key questions: What are foundation models in RS? Why are foundation models needed in RS? How can we effectively guide junior researchers in gaining a comprehensive and practical understanding of foundation models in RS applications? More specifically, we begin by outlining the background and motivation, emphasizing the importance of foundation models in RS. We then review existing foundation models in RS, systematically categorizing them into unimodal and multimodal approaches. Additionally, we provide a tutorial-like section to guide researchers, especially beginners, on how to train foundation models in RS and apply them to real-world tasks. The survey aims to equip researchers in RS with a deeper and more efficient understanding of foundation models, enabling them to get started easily and effectively apply these models across various RS applications.

Federated learning (FL) has arisen as an alternative to collecting large amounts of data in a central place to train a machine learning (ML) model. FL is privacy-friendly, allowing multiple parties to collaboratively train an ML model without exchanging or transmitting their training data. For this purpose, an aggregator iteratively coordinates the training process among parties, and parties simply share with the aggregator model updates, which contain information pertinent to the model such as neural network weights. Besides privacy, generalization has been another key driver for FL: parties who do not have enough data to train a good performing model by themselves can now engage in FL to obtain an ML model suitable for their tasks. Products and real applications in the industry and consumer space have demonstrated the power of this learning paradigm. Recently, foundation models have taken the AI community by storm, promising to solve the shortage of labeled data. A foundation model is a powerful model that can be recycled for a variety of use cases by applying techniques such as zero-shot learning and full or parameter-efficient fine tuning. The premise is that the amount of data required to fine tune a foundation model for a new task is much smaller than fully training a traditional model from scratch. The reason why this is the case is that a good foundation model has already learned relevant general representations, and thus, adapting it to a new task only requires a minimal number of additional samples. This raises the question: Is FL still alive in the era of foundation models? In this talk, I will address this question. I will present some use cases where FL is very much alive. In these use cases, finding a foundation model with a desired representation is difficult if not impossible. With this pragmatic point of view, I hope to shed some light into a real use case where disparate private data is available in isolation at different parties and where labels may be located at a single party that doesn’t have any other information, making it impossible for a single party to train a model on its own. Furthermore, in some vertically-partitioned scenarios, cleaning data is not an option due to privacy-related reasons and it is not clear how to apply foundation models. Finally, I will also go over a few other requirements that are often overlooked, such as unlearning of data and its implications for the lifecycle management of FL and systems based on foundation models.

Предложена и обоснована новая пространственная ме­ханическая динамическая модель оснований сооружений атомных станций.
 В настоящее время при выполнении практических расчётов широко применяется модель оснований соору­жений атомных станций, приведённая в [1]. В этой модели мгновенные жёсткости основания при вращательных движениях жёсткого невесомого штампа функционально зависят от массы сооружения и от моментов инерции масс сооружения относительно координатных осей, что противоречит физической сути понятия мгновенных жёст­костей основания при вращательных движениях жёсткого невесомого штампа на поверхности инерционного полу­пространства.
 В свете вышеизложенного разработка динамической механической модели основания, устраняющей упомянутые несоответствия, представляется важной задачей, имеющей несомненную научную и практическую ценность
 Для обоснования проектных решений фундаментных конструкций сооружений необходимо определить величи­ны внутренних усилий, возникающих в их сечениях. При учёте конечной жёсткости фундаментных конструкций с применением метода конечных элементов необходимо установить закон распределения квазистатических и мгновенных жёстокостей грунтов основания по подошве фундаментной плиты.
 Известно, что параметры модели основания по существу должны имитировать параметры реакции основания жёст­кого невесомого штампа при его единичных смещениях и скоростях (линейных и угловых) по и относительно коор­динатных осей.
 В работе определены и обоснованы параметры модели основания, закон распределения интегральных жёсткостей по поверхности контакта. На примере сопоставления расчётов систем реакторного отделения совместно с основаниями, параметры которых были установлены по [1; 2], обоснована достоверность предлагаемой модели.

Numerous pathology foundation models have been developed to extract clinically relevant information. There is currently limited literature independently evaluating these foundation models on external cohorts and clinically relevant tasks to uncover adjustments for future improvements. Here we benchmark 19 histopathology foundation models on 13 patient cohorts with 6,818 patients and 9,528 slides from lung, colorectal, gastric and breast cancers. The models were evaluated on weakly supervised tasks related to biomarkers, morphological properties and prognostic outcomes. We show that a vision-language foundation model, CONCH, yielded the highest overall performance when compared with vision-only foundation models, with Virchow2 as close second, although its superior performance was less pronounced in low-data scenarios and low-prevalence tasks. The experiments reveal that foundation models trained on distinct cohorts learn complementary features to predict the same label, and can be fused to outperform the current state of the art. An ensemble combining CONCH and Virchow2 predictions outperformed individual models in 55% of tasks, leveraging their complementary strengths in classification scenarios. Moreover, our findings suggest that data diversity outweighs data volume for foundation models.

Study question Can a generalizable computer vision foundation model be trained using self-supervised learning on time-lapse embryo images to perform multiple clinically relevant downstream tasks? Summary answer We developed FEMI, a foundation model trained on eight million time-lapse images, to perform multiple clinical tasks, including blastocyst quality scoring, ploidy prediction, and segmentation. What is known already In vitro fertilization success critically depends on choosing viable embryos, a process hampered by current limited diagnostic tools, high costs, and ethical concerns. In recent years, various medical fields have increasingly explored foundation models using vision transformer architectures. These models, trained in a self-supervised manner on vast unlabeled image datasets, perform various clinically relevant tasks. Once trained on a massive unlabeled dataset, the encoder portion of the foundation model can be extracted and subsequently fine-tuned with a labeled dataset to perform various clinically relevant tasks like classification, regression, and segmentation. Study design, size, duration The foundation model was trained on 8 million Embryoscope® (E-SD) and Embryoscope+® (E+) images spanning clinics in the United States, Canada, and Europe. Datasets contained various additional information, such as ploidy status, blastocyst scores (numerical values from 3 to 14 based on Zhan et al. 2020), and segmentation masks (for trophectoderm [TE], inner cell mass [ICM], and zona pellucida [ZP]) that were used for training downstream tasks. Participants/materials, setting, methods A masked autoencoder architecture is trained on time-lapse images to create a foundation model (FEMI). The encoder from the autoencoder is extracted and fine-tuned on three image-based downstream tasks: ploidy prediction, blastocyst scoring, and embryo component segmentation. The performance of the fine-tuned foundation model is compared to VGG16 architectures, specifically trained for each downstream task. We evaluated performances using the area under the receiver-operating-characteristic (AUROC), mean absolute error (MAE), and mean intersection over union (mIoU). Main results and the role of chance The training dataset for the downstream tasks consisted of image data and labels, including PGT-A ploidy results (euploid or aneuploid), blastocyst scores (3-14), and segmentation masks. No clinical data like maternal age was used in order to assess FEMI’s learning capabilities from only time-lapse images against VGG16 model baselines. Both FEMI and baseline models used the same data splits for consistent comparisons. For ploidy prediction, models trained on a Weill Cornell Medicine (WCM) dataset were validated using WCM, Florida, and Spain data. FEMI achieved a 0.610 ± 0.004 AUROC, outperforming the baseline’s 0.590 ± 0.005. In blastocyst score prediction, FEMI attained a superior MAE of 0.099 ± 0.002 compared to the baseline’s 0.118 ± 0.001. For embryo segmentation (TE, ICM, ZP), a publicly available dataset from Simon Fraser University was split for training and validation. FEMI exceeded the baseline in mIoU for TE segmentation (0.738 ± 0.002 vs. 0.726 ± 0.002) and was comparable in ICM (0.832 ± 0.008 vs. 0.821 ± 0.011) and ZP segmentation (0.779 ± 0.002 vs. 0.778 ± 0.010). Limitations, reasons for caution The current version of FEMI is trained on a subset of our available datasets and can be improved through further training. Moreover, the downstream ploidy and blastocyst score models may be biased by errors in PGT results and the subjectivity of embryologists, respectively. Wider implications of the findings A generalizable foundational model for IVF time-lapse imaging aids clinicians in embryo selection by providing various clinical insights for better decision-making. FEMI, once fully trained, will be publicly accessible to the scientific community allowing for researchers to fine-tune FEMI on their own clinic-specific applications with their own image datasets. Trial registration number not applicable

• The objectives of this study match the CIE content as it provides academcians and practioners with innovative and helpful information on advanced computing technology in the industry. • Foundation models are large-scale machine learning models that have been trained on large amounts of data to perform a variety of tasks. • FMs are used to support management and operations in supply chain and logistics management and operations. • The paper is based on research conducted by the authors with several Italian and European organizations under a grant from the European Union's Next GenerationUE initiative. • The paper concludes with a real-world industrial case study to further substantiate these claims. The organizational environment is subject to constant change, driven by rapid technological progress and the advent of Industry 5.0. This dynamic scenario compels authors and practitioners in the fields of logistics and supply chain management and operations (LSCM) to explore the transformative impact of foundation models (FMs) and artificial intelligence (AI) on these areas. The integration of AI FMs, coupled with digital twins (DT) and cyber-physical systems (CPS), will not only optimize current processes but also fundamentally reshape the future of digital engineering (DE) in LSCM. Understanding the opportunities and challenges with FMs is critical to the strategic positioning in an ever-evolving marketplace where Industry 5.0 technologies drive innovation and efficiency. Organizations can gain a competitive advantage by analyzing the opportunities and risks of integrating FMs into LSCM operations and leveraging their ability to improve decision making and enhance predictive analytics and real-time monitoring through DT and CPS. This paper serves as a comprehensive and informative guide for evaluating the transformative potential of FMs in redesigning LSCM operations in the context of Industry 5.0, highlighting critical applications, exploring potential benefits and challenges, and pointing to upcoming innovations such as AI-driven DT and smart cyber-physical systems that are revolutionizing supply chain (SC) processes. The detailed analysis based on the Supply Chain Operations Reference (SCOR) components shows that FM-based solutions, supported by AI and Industry 5.0 technologies, can significantly improve LSCM business processes. This paper presents an integrated functional framework and technical architecture for implementing FM in LSCM, emphasizing the role of DT and CPS in enabling smart, adaptive, and resilient SC. The paper concludes with an industrial case study that further substantiates these claims and shows the practical application of FM in a shipbuilding organization. The case study describes successful approaches to implementing and effectively utilizing AI and DT. It provides a practical, functional, and technical framework for applying the transformative impact of FMs on LSCM within the Industry 5.0 paradigm. This integration highlights the synergy between FM, AI, DT, and CPS and paves the way. It paves the way for a more innovative, sustainable, and competitive management of supply networks and their operations.

We survey applications of pretrained foundation models in robotics. Traditional deep learning models in robotics are trained on small datasets tailored for specific tasks, which limits their adaptability across diverse applications. In contrast, foundation models pretrained on internet-scale data appear to have superior generalization capabilities, and in some instances display an emergent ability to find zero-shot solutions to problems that are not present in the training data. Foundation models may hold the potential to enhance various components of the robot autonomy stack, from perception to decision-making and control. For example, large language models can generate code or provide common sense reasoning, while vision-language models enable open-vocabulary visual recognition. However, significant open research challenges remain, particularly around the scarcity of robot-relevant training data, safety guarantees and uncertainty quantification, and real-time execution. In this survey, we study recent papers that have used or built foundation models to solve robotics problems. We explore how foundation models contribute to improving robot capabilities in the domains of perception, decision-making, and control. We discuss the challenges hindering the adoption of foundation models in robot autonomy and provide opportunities and potential pathways for future advancements. The GitHub project corresponding to this paper can be found here: https://github.com/robotics-survey/Awesome-Robotics-Foundation-Models.

Robust assessment of artificial intelligence (AI) models in medical imaging is paramount for reliable clinical integration. This international collaborative review paper provides an overview of key evaluation metrics across diverse tasks, including classification, regression, survival analysis, detection, and segmentation, as well as specialized metrics for calibration, foundation models, large language models, and synthetic images. Challenges of comparing models statistically and translating metric scores to clinical practice are also discussed. For each section, the paper outlines fundamental metrics, identifies common pitfalls and misapplications, and offers recommendations for more robust evaluations. Key recommendations often involve utilizing multiple, complementary metrics tailored to the specific task and dataset properties, transparent reporting of methodology, and critically, considering the clinical utility and real-world implications of model performance. Ultimately, effective evaluation requires a comprehensive, context-aware approach that goes beyond statistical metrics to ensure model trust and clinical relevance. The authors hope this review will serve as a practical reference for researchers aiming to implement robust and clinically meaningful AI evaluations in medical imaging. • This review outlines the key metrics for evaluating medical imaging AI. • Common pitfalls and misapplications are critically examined, with corresponding recommendations provided for each. • Appropriate metric selection depends on the specific AI task. • Foundation and generative models require broader evaluation methods, beyond traditional evaluation metrics. • A multi-metric, context-aware evaluation is essential for reliability.

ObjectiveTo assess the performance of the current foundation models in histopathology. Patients and MethodsThe assessment involves a comprehensive evaluation of some foundation models, such as the CLIP derivatives, namely PLIP and BiomedCLIP, which were fine-tuned on data scraped from the internet. The comparison is performed against simpler and nonfoundational histology models that are trained on well-curated data, eg, the cancer genome atlas. All models are evaluated on 8 datasets, 4 of which are internal histology datasets collected and curated at Mayo Clinic, and 4 well-known public datasets: PANDA, BRACS, CAMELYON16, and DigestPath. Evaluation metrics include accuracy and macro-averaged F1 score, using a majority vote among top-k (eg, MV@5) at the whole slide image/patch levels. Moreover, all models are evaluated in classification settings. This detailed analysis allows for a deep understanding of each model’s performance across various datasets. ResultsIn various evaluation tasks, domain-specific (and nonfoundational) models like DinoSSLPath and KimiaNet outperform general-purpose foundation models. The DinoSSLPath excels in whole slide image-level retrieval for internal colorectal cancer and liver datasets with MV@5 macro-averaged F1 scores of 63% and 74%, respectively. The KimiaNet leads in breast and skin cancer tasks with respective Top-1 and MV@5 scores of 56% and 70%, respectively and scores 75% on the public CAMELYON16 dataset. Similar trends are observed in patch-level metrics, highlighting the advantage of using specialized datasets like the cancer genome atlas for histopathological analysis. ConclusionTo enable effective vision-language foundation models in biomedicine, high-quality, multi-modal medical datasets are essential. These datasets serve as the substrate for training models capable of translating research into clinical practice. Of importance, the alignment (correspondence) between textual and visual data—often diagnostic—is critical and requires validation by domain experts. Thus, advancing foundation models in this field necessitates collaborative efforts in data curation and validation.

Foundation models have revolutionized natural language processing and computer vision, yet their potential for tabular data, particularly in telecommunications, remains underexplored. We apply foundation models to large-scale telco drive test data, achieving up to $30 \%$ relative gain in $R^{2}$ over state-of-the-art methods like XGBoost. A central focus is transforming numeric telco data into tokens, enabling meaningful embeddings. Unlike NLP and computer vision, the telco domain lacks pretrained models, necessitating training from scratch to capture domain-specific patterns. We also detail data preprocessing and sequence conversion techniques tailored for foundation models, as well as the trade-offs of various numeric binning methods (e.g., cut, qcut, Lloyd-Max quantization) affecting data balance and token frequency. Beyond KPI prediction, we demonstrate the ability of the foundation model as a network optimization simulator, offering significant advantages over manual tuning. Our results show that foundation models excel on large datasets with millions of rows and high categorical complexity, consistently outperforming XGBoost, which remains more effective on simpler datasets. Furthermore, foundation models achieve up to $13 \%$ relative gain in $R^{2}$ in public tabular datasets, underscoring their versatility for complex, high-dimensional data challenges.

Vision foundation models in remote sensing have been extensively studied due to their superior generalization on various downstream tasks. Synthetic Aperture Radar (SAR) offers all-day, all-weather imaging capabilities, providing significant advantages for Earth observation. However, establishing a foundation model for SAR image interpretation inevitably encounters the challenges of insufficient information utilization and poor interpretability. In this paper, we propose a remote sensing foundation model based on complex-valued SAR data, which simulates the polarimetric decomposition process for pre-training, i.e., characterizing pixel scattering intensity as a weighted combination of scattering bases and scattering coefficients, thereby endowing the foundation model with physical interpretability. Specifically, we construct a series of scattering queries, each representing an independent and meaningful scattering basis, which interact with SAR features in the scattering query decoder and output the corresponding scattering coefficient. To guide the pre-training process, polarimetric decomposition loss and power self-supervised loss are constructed. The former aligns the predicted coefficients with Yamaguchi coefficients, while the latter reconstructs power from the predicted coefficients and compares it to the input image's power. The performance of our foundation model is validated on nine typical downstream tasks, achieving state-of-the-art results. Notably, the foundation model can extract stable feature representations and exhibits strong generalization, even in data-scarce conditions.

With the recent rapid advances of revolutionary AI models such as ChatGPT, foundation models have become a main topic for the discussion of future AI. Despite the excitement, the success is still limited to specific types of tasks. Particularly, ChatGPT and similar foundation models have unique characteristics that are difficult to replicate for most geospatial tasks. This paper envisions several major challenges and opportunities in the creation of geospatial foundation (geo-foundation) models, as well as potential future adoption scenarios. We also expect that a major success story is necessary for geo-foundation models to take off in the long term.

With the rapid development of artificial intelligence, computational pathology has been seamlessly integrated into the entire clinical workflow, which encompasses diagnosis, treatment, prognosis, and biomarker discovery. This integration has significantly enhanced clinical accuracy and efficiency while reducing the workload for clinicians. Traditionally, research in this field has depended on the collection and labeling of large datasets for specific tasks, followed by the development of task-specific computational pathology models. However, this approach is labor intensive and does not scale efficiently for open-set identification or rare diseases. Given the diversity of clinical tasks, training individual models from scratch to address the whole spectrum of clinical tasks in the pathology workflow is impractical, which highlights the urgent need to transition from task-specific models to foundation models (FMs). In recent years, pathological FMs have proliferated. These FMs can be classified into three categories, namely, pathology image FMs, pathology image–text FMs, and pathology image–gene FMs, each of which results in distinct functionalities and application scenarios. This review provides an overview of the latest research advancements in pathological FMs, with a particular emphasis on their applications in oncology. The key challenges and opportunities presented by pathological FMs in precision oncology are also explored.