{"total":102,"rows":[{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161,"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":"2309.07778","title":"Virchow: A Million-Slide Digital Pathology Foundation Model","created":"2023-09-14","cited_by_count":90,"area":null},{"id":"2405.03162","title":"Advancing Multimodal Medical Capabilities of Gemini","created":"2024-05-06","cited_by_count":90,"area":null},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86,"area":null},{"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":"2311.12751","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","created":"2023-11-21","cited_by_count":42,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2403.15992","title":"BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval","created":"2024-03-24","cited_by_count":30,"area":null},{"id":"2505.20510","title":"CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic","created":"2025-05-26","cited_by_count":29,"area":null},{"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":"2406.12723","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","created":"2024-06-18","cited_by_count":24,"area":null},{"id":"2406.06393","title":"STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"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":"2405.17537","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2412.02621","title":"Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions","created":"2024-12-03","cited_by_count":18,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2408.09530","title":"PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding","created":"2024-08-18","cited_by_count":16,"area":null},{"id":"2501.15724","title":"A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks","created":"2025-01-27","cited_by_count":16,"area":null},{"id":"2407.01791","title":"{\\mu}-Bench: A Vision-Language Benchmark for Microscopy Understanding","created":"2024-07-01","cited_by_count":15,"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":"2510.15710","title":"UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2411.09894","title":"Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2506.05127","title":"PixCell: A generative foundation model for digital histopathology images","created":"2025-06-05","cited_by_count":11,"area":null},{"id":"2406.15303","title":"AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification","created":"2024-06-18","cited_by_count":10,"area":null},{"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":"2503.09091","title":"Multi-Modal Foundation Models for Computational Pathology: A Survey","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","cited_by_count":9,"area":null},{"id":"2407.13708","title":"Are We Ready for Out-of-Distribution Detection in Digital Pathology?","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2503.14377","title":"Advancing Medical Representation Learning Through High-Quality Data","created":"2025-03-18","cited_by_count":8,"area":null},{"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":"2508.01490","title":"A Large-Scale Benchmark of Cross-Modal Learning for Histology and Gene Expression in Spatial Transcriptomics","created":"2025-08-02","cited_by_count":8,"area":null},{"id":"2508.09177","title":"Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2407.07360","title":"Towards a text-based quantitative and explainable histopathology image analysis","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2412.12661","title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","created":"2024-12-17","cited_by_count":6,"area":null},{"id":"2512.21331","title":"TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2505.10993","title":"Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"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":"2407.09030","title":"CAMP: Continuous and Adaptive Learning Model in Pathology","created":"2024-07-12","cited_by_count":4,"area":null},{"id":"2505.15687","title":"Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.20254","title":"Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2404.07676","title":"Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2407.07504","title":"Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencoder","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2502.20823","title":"Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2503.06482","title":"PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2506.18072","title":"Multimodal Medical Image Binding via Shared Text Embeddings","created":"2025-06-22","cited_by_count":3,"area":null},{"id":"2509.20022","title":"PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Prediction","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2603.02790","title":"Designing UNICORN: a Unified Benchmark for Imaging in Computational Pathology, Radiology, and Natural Language","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2407.14904","title":"Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2412.16715","title":"From Histopathology Images to Cell Clouds: Learning Slide Representations with Hierarchical Cell Transformer","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2501.04184","title":"MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2502.07221","title":"Histopathology Multi-modal Embedding for Pathology Composed Retrieval","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2505.06898","title":"Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration","created":"2025-05-11","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":"2508.14588","title":"Controllable Latent Space Augmentation for Digital Pathology","created":"2025-08-20","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":"2608.30420","title":"Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2406.07450","title":"Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning","created":"2024-06-11","cited_by_count":1,"area":null},{"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":"2502.12948","title":"Fake It Till You Make It: Using Synthetic Data and Domain Knowledge for Improved Text-Based Learning for LGE Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.01654","title":"A Shared Encoder Approach to Multimodal Representation Learning","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2504.16181","title":"CLIP-IT: CLIP-based Pairing for Histology Images Classification","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2507.03532","title":"PhenoBench: A Comprehensive Benchmark for Cell Phenotyping","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2511.18519","title":"CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2602.20873","title":"MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.15276","title":"Dataset Diversity Metrics and Impact on Classification Models","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2410.15886","title":"Foundation Models for Slide-level Cancer Subtyping in Digital Pathology","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2503.02064","title":"CrossFusion: A Multi-Scale Cross-Attention Convolutional Fusion Model for Cancer Survival Prediction","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.10731","title":"Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2504.15545","title":"VLM-based Prompts as the Optimal Assistant for Unpaired Histopathology Virtual Staining","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2504.19443","title":"CLIP-KOA: Enhancing Knee Osteoarthritis Diagnosis with Multi-Modal Learning and Symmetry-Aware Loss Functions","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2505.06710","title":"SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2508.14537","title":"LanGuSTE: Language-Guided Coarse-to-Fine Patch Selection for Efficient Whole Slide Image Analysis","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2508.15256","title":"Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model for Anomaly Detection in Pathology Images","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2508.15904","title":"Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.15482","title":"Comparing Computational Pathology Foundation Models using Representational Similarity Analysis","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.15164","title":"Hyperparameter Optimization and Reproducibility in Deep Learning Model Training","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2602.13944","title":"Fusing Pixels and Genes: Spatially-Aware Learning in Computational Pathology","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2602.16422","title":"Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.13787","title":"Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspective","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.21504","title":"Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.17570","title":"PBSBench: A Multi-Level Vision-Language Framework and Benchmark for Hematopathology Whole Slide Image Interpretation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.23982","title":"Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.10778","title":"From Patches to Patients: A study of the tile-to-slide performance transferability in Digital Pathology","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.19966","title":"Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.28697","title":"Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.01407","title":"Training-Free Out-of-Distribution Detection for Pathology Whole-Slide Images","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.03508","title":"From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.26382","title":"VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04698","title":"LookThere! Sparse Vision by Reinforced Selection","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.31040","title":"Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34451","title":"Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37682","title":"Med-RADIO: Reducing All Medical Domains Into One via Multi-Teacher Distillation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}