{"total":134,"rows":[{"id":"2406.16192","title":"HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis","created":"2024-06-23","cited_by_count":107,"area":null},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2405.10254","title":"PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology","created":"2024-05-16","cited_by_count":85,"area":null},{"id":"2308.07898","title":"A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision","created":"2023-08-15","cited_by_count":78,"area":"mllm"},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77,"area":null},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76,"area":null},{"id":"2405.11643","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":72,"area":null},{"id":"2407.15362","title":"A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model","created":"2024-07-22","cited_by_count":59,"area":null},{"id":"2307.12914","title":"Towards a Visual-Language Foundation Model for Computational Pathology","created":"2023-07-24","cited_by_count":52,"area":null},{"id":"2309.00748","title":"PathLDM: Text conditioned Latent Diffusion Model for Histopathology","created":"2023-09-01","cited_by_count":52,"area":"diffusion"},{"id":"2405.11618","title":"Transcriptomics-guided Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":51,"area":null},{"id":"2403.05396","title":"HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction","created":"2024-03-08","cited_by_count":43,"area":null},{"id":"2308.15474","title":"A General-Purpose Self-Supervised Model for Computational Pathology","created":"2023-08-29","cited_by_count":42,"area":null},{"id":"2405.17766","title":"SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals","created":"2024-05-28","cited_by_count":41,"area":null},{"id":"2406.10395","title":"BrainSegFounder: Towards 3D Foundation Models for Neuroimage Segmentation","created":"2024-06-14","cited_by_count":39,"area":null},{"id":"2407.05603","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","created":"2024-07-08","cited_by_count":34,"area":null},{"id":"2311.16480","title":"WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images","created":"2023-11-27","cited_by_count":31,"area":null},{"id":"2404.15272","title":"CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2406.19578","title":"PathAlign: A vision-language model for whole slide images in histopathology","created":"2024-06-27","cited_by_count":30,"area":"mllm"},{"id":"2502.08391","title":"ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification","created":"2025-02-12","cited_by_count":28,"area":null},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2506.20964","title":"Evidence-based diagnostic reasoning with multi-agent copilot for human pathology","created":"2025-06-26","cited_by_count":27,"area":"lr"},{"id":"2312.15010","title":"SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology","created":"2023-12-22","cited_by_count":25,"area":null},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2312.07814","title":"A Foundational Multimodal Vision Language AI Assistant for Human Pathology","created":"2023-12-13","cited_by_count":21,"area":null},{"id":"2412.13126","title":"Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis","created":"2024-12-17","cited_by_count":21,"area":"mllm"},{"id":"2406.05205","title":"CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment","created":"2024-06-07","cited_by_count":20,"area":"mllm"},{"id":"2411.14001","title":"Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Prediction","created":"2024-11-21","cited_by_count":20,"area":null},{"id":"2411.14743","title":"FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification","created":"2024-11-22","cited_by_count":20,"area":null},{"id":"2412.02601","title":"MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images","created":"2024-12-03","cited_by_count":17,"area":null},{"id":"2408.11505","title":"MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2403.08967","title":"PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning","created":"2024-03-13","cited_by_count":14,"area":null},{"id":"2404.09942","title":"Knowledge-enhanced Visual-Language Pretraining for Computational Pathology","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2409.09369","title":"Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology","created":"2024-09-14","cited_by_count":14,"area":null},{"id":"2407.10814","title":"Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2308.13182","title":"Structural Cycle GAN for Virtual Immunohistochemistry Staining of Gland Markers in the Colon","created":"2023-08-25","cited_by_count":10,"area":null},{"id":"2410.10573","title":"Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification","created":"2024-10-14","cited_by_count":10,"area":"mllm"},{"id":"2411.18101","title":"Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis","created":"2024-11-27","cited_by_count":10,"area":null},{"id":"2311.06176","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers","created":"2023-11-10","cited_by_count":9,"area":null},{"id":"2408.14496","title":"A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Models","created":"2024-08-23","cited_by_count":9,"area":"mllm"},{"id":"2503.09091","title":"Multi-Modal Foundation Models for Computational Pathology: A Survey","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2503.12990","title":"How Good is my Histopathology Vision-Language Foundation Model? A Holistic Benchmark","created":"2025-03-17","cited_by_count":8,"area":"mllm"},{"id":"2504.01009","title":"GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2506.09095","title":"Foundation Models in Medical Imaging: A Review and Outlook","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2402.06188","title":"A self-supervised framework for learning whole slide representations","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2409.15574","title":"Clinical-grade Multi-Organ Pathology Report Generation for Multi-scale Whole Slide Images via a Semantically Guided Medical Text Foundation Model","created":"2024-09-23","cited_by_count":6,"area":"mllm"},{"id":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6,"area":"mllm"},{"id":"2510.00053","title":"DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2512.05391","title":"LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models","created":"2025-12-05","cited_by_count":6,"area":"mllm"},{"id":"2603.06658","title":"ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging","created":"2026-03-01","cited_by_count":6,"area":null},{"id":"2403.15836","title":"VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image Classification","created":"2024-03-23","cited_by_count":5,"area":"mllm"},{"id":"2502.00568","title":"Generating crossmodal gene expression from cancer histopathology improves multimodal AI predictions","created":"2025-02-01","cited_by_count":5,"area":null},{"id":"2403.12537","title":"Prompt-Guided Foundation Model Tuning for Pathology Image Classification","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2403.14616","title":"Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2408.15032","title":"Mamba2MIL: State Space Duality Based Multiple Instance Learning for Computational Pathology","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2411.15076","title":"RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2502.11093","title":"Text-Promptable Propagation for Referring Medical Image Sequence Segmentation","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2508.01602","title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2512.17621","title":"PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology","created":"2025-12-19","cited_by_count":4,"area":"mllm"},{"id":"2409.09052","title":"OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed Tomography","created":"2024-08-30","cited_by_count":3,"area":"mllm"},{"id":"2410.16820","title":"AttriPrompter: Auto-Prompting with Attribute Semantics for Zero-shot Nuclei Detection via Visual-Language Pre-trained Models","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2502.07409","title":"MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification","created":"2025-02-11","cited_by_count":3,"area":"mllm"},{"id":"2502.16223","title":"Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection","created":"2025-02-22","cited_by_count":3,"area":"mllm"},{"id":"2505.00134","title":"Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design","created":"2025-04-30","cited_by_count":3,"area":"mllm"},{"id":"2602.18773","title":"LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology","created":"2026-02-21","cited_by_count":3,"area":"agents"},{"id":"2603.23067","title":"MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding","created":"2026-03-24","cited_by_count":3,"area":"mllm"},{"id":"2309.01740","title":"An Empirical Analysis for Zero-Shot Multi-Label Classification on COVID-19 CT Scans and Uncurated Reports","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2401.15526","title":"Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy","created":"2024-01-27","cited_by_count":2,"area":null},{"id":"2405.14230","title":"Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2503.09498","title":"Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.01984","title":"Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2505.04672","title":"Histo-Miner: Deep learning based tissue features extraction pipeline from H&E whole slide images of cutaneous squamous cell carcinoma","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2508.03277","title":"Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classification","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.12108","title":"VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine","created":"2025-08-16","cited_by_count":2,"area":null},{"id":"2511.13099","title":"MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2603.08328","title":"Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2603.10526","title":"Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.09169","title":"UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2403.05379","title":"Self-Supervised Multiple Instance Learning for Acute Myeloid Leukemia Classification","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2404.16397","title":"Deep Learning-based Prediction of Breast Cancer Tumor and Immune Phenotypes from Histopathology","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2406.18249","title":"Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2408.08847","title":"HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2410.15881","title":"MI-VisionShot: Few-shot adaptation of vision-language models for slide-level classification of histopathological images","created":"2024-10-21","cited_by_count":1,"area":"mllm"},{"id":"2410.19820","title":"Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2502.16055","title":"MedForge: Building Medical Foundation Models Like Open Source Software Development","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2503.00804","title":"DELST: Dual Entailment Learning for Hyperbolic Image-Gene Pretraining in Spatial Transcriptomics","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2503.13799","title":"SMILE: a Scale-aware Multiple Instance Learning Method for Multicenter STAS Lung Cancer Histopathology Diagnosis","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.03474","title":"Multi-encoder nnU-Net outperforms transformer models with self-supervised pretraining","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.15627","title":"ZeroSlide: Is Zero-Shot Classification Adequate for Lifelong Learning in Whole-Slide Image Analysis in the Era of Pathology Vision-Language Foundation Models?","created":"2025-04-22","cited_by_count":1,"area":"mllm"},{"id":"2507.10250","title":"DepViT-CAD: Deployable Vision Transformer-Based Cancer Diagnosis in Histopathology","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.01293","title":"GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2508.02220","title":"Welcome New Doctor: Continual Learning with Expert Consultation and Autoregressive Inference for Whole Slide Image Analysis","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.13482","title":"Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.06105","title":"PathoHR: Hierarchical Reasoning for Vision-Language Models in Pathology","created":"2025-09-07","cited_by_count":1,"area":"lr"},{"id":"2601.10386","title":"Handling Missing Modalities in Multimodal Survival Prediction for Non-Small Cell Lung Cancer","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2605.01144","title":"Semantic Context-aware mOdality fUsion Transformer (SCOUT): A Context-Aware Multimodal Transformer for Concept-Grounded Pathology Report Generation","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2607.12278","title":"Auditing Data Leakage in Whole-Slide Image Multimodal Benchmarks","created":"2026-07-14","cited_by_count":1,"area":"mllm"},{"id":"2312.01435","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers and BERT","created":"2023-12-03","cited_by_count":0,"area":null},{"id":"2312.07125","title":"TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2406.12897","title":"Advancing Histopathology-Based Breast Cancer Diagnosis: Insights into Multi-Modality and Explainability","created":"2024-06-07","cited_by_count":0,"area":null}],"next_cursor":"100"}