{"total":78,"rows":[{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2405.14137","title":"RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports","created":"2024-05-23","cited_by_count":30,"area":"mllm"},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2405.11793","title":"MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2409.03868","title":"Few-shot Adaptation of Medical Vision-Language Models","created":"2024-09-05","cited_by_count":24,"area":"mllm"},{"id":"2502.14807","title":"FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis","created":"2025-02-20","cited_by_count":24,"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":"2408.16769","title":"PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning","created":"2024-08-29","cited_by_count":17,"area":"mllm"},{"id":"2408.07440","title":"BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning","created":"2024-08-14","cited_by_count":16,"area":"safety"},{"id":"2505.24693","title":"Conformal Prediction for Zero-Shot Models","created":"2025-05-30","cited_by_count":15,"area":"mllm"},{"id":"2406.09317","title":"Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model","created":"2024-06-13","cited_by_count":12,"area":"mllm"},{"id":"2501.10834","title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","created":"2025-01-18","cited_by_count":11,"area":"mllm"},{"id":"2404.03618","title":"DeViDe: Faceted medical knowledge for improved medical vision-language pre-training","created":"2024-04-04","cited_by_count":10,"area":"mllm"},{"id":"2408.05618","title":"UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling","created":"2024-08-10","cited_by_count":10,"area":null},{"id":"2412.09402","title":"MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2506.06076","title":"Full Conformal Adaptation of Medical Vision-Language Models","created":"2025-06-06","cited_by_count":9,"area":"mllm"},{"id":"2506.18378","title":"Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review","created":"2025-06-23","cited_by_count":9,"area":"mllm"},{"id":"2409.01883","title":"Boosting Vision-Language Models for Histopathology Classification: Predict all at once","created":"2024-09-03","cited_by_count":8,"area":"mllm"},{"id":"2506.09095","title":"Foundation Models in Medical Imaging: A Review and Outlook","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2506.17503","title":"Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction","created":"2025-06-20","cited_by_count":8,"area":"mllm"},{"id":"2408.10894","title":"ViLReF: An Expert Knowledge Enabled Vision-Language Retinal Foundation Model","created":"2024-08-20","cited_by_count":7,"area":"mllm"},{"id":"2506.08900","title":"MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2506.17500","title":"Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation","created":"2025-06-20","cited_by_count":7,"area":"mllm"},{"id":"2508.16129","title":"Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2408.14770","title":"Text-guided Foundation Model Adaptation for Long-Tailed Medical Image Classification","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2501.15798","title":"MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining","created":"2025-01-27","cited_by_count":5,"area":"mllm"},{"id":"2503.01020","title":"Delving into Out-of-Distribution Detection with Medical Vision-Language Models","created":"2025-03-02","cited_by_count":5,"area":"mllm"},{"id":"2505.12887","title":"RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2506.19320","title":"Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities","created":"2025-06-24","cited_by_count":5,"area":"mllm"},{"id":"2403.10823","title":"VisionCLIP: An Med-AIGC based Ethical Language-Image Foundation Model for Generalizable Retina Image Analysis","created":"2024-03-16","cited_by_count":4,"area":null},{"id":"2501.12266","title":"CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification","created":"2025-01-21","cited_by_count":4,"area":"mllm"},{"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":"2508.03734","title":"A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models","created":"2025-07-31","cited_by_count":4,"area":null},{"id":"2601.12493","title":"Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation","created":"2026-01-18","cited_by_count":4,"area":"mllm"},{"id":"2501.18291","title":"CueTip: An Interactive and Explainable Physics-aware Pool Assistant","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2505.12233","title":"PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning","created":"2025-05-18","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":"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":"2504.05227","title":"A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2511.15943","title":"Boosting Medical Visual Understanding From Multi-Granular Language Learning","created":"2025-11-20","cited_by_count":2,"area":null},{"id":"2602.17535","title":"LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2410.13242","title":"Fundus to Fluorescein Angiography Video Generation as a Retinal Generative Foundation Model","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2507.04259","title":"An Explainable Transformer Model for Alzheimer's Disease Detection Using Retinal Imaging","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2508.10549","title":"PSScreen: Partially Supervised Multiple Retinal Disease Screening","created":"2025-08-14","cited_by_count":1,"area":"distill"},{"id":"2512.14499","title":"Native Intelligence Emerges from Large-Scale Clinical Practice: A Retinal Foundation Model with Deployment Efficiency","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2604.02448","title":"Managing Diabetic Retinopathy with Deep Learning: A Data Centric Overview","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.27916","title":"OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Models","created":"2026-05-27","cited_by_count":1,"area":"mllm"},{"id":"2312.13316","title":"ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training","created":"2023-12-20","cited_by_count":0,"area":"mllm"},{"id":"2506.22149","title":"RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2507.01055","title":"Prompt Mechanisms in Medical Imaging: A Comprehensive Survey","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2509.08624","title":"UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.07277","title":"Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.22589","title":"PSScreen V2: Partially Supervised Multiple Retinal Disease Screening","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.13008","title":"TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.14774","title":"Does medical specialization of VLMs enhance discriminative power?: A comprehensive investigation through feature distribution analysis","created":"2026-01-21","cited_by_count":0,"area":"mllm"},{"id":"2602.19471","title":"Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model","created":"2026-02-23","cited_by_count":0,"area":"mllm"},{"id":"2602.23297","title":"PRIMA: Pre-Training with Risk-Integrated Image--Metadata Alignment for Medical Diagnosis with LLM-Based Feature Aggregation","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.02959","title":"Semi-Supervised Few-Shot Adaptation of Vision-Language Models","created":"2026-03-03","cited_by_count":0,"area":"mllm"},{"id":"2603.08434","title":"Information Maximization for Long-Tailed Semi-Supervised Domain Generalization","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.09101","title":"MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration","created":"2026-03-10","cited_by_count":0,"area":"mllm"},{"id":"2603.13403","title":"Diabetic Retinopathy Grading with CLIP-based Ranking-Aware Adaptation:A Comparative Study on Fundus Image","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.08936","title":"M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model","created":"2026-04-10","cited_by_count":0,"area":"moe"},{"id":"2604.17629","title":"BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs","created":"2026-04-19","cited_by_count":0,"area":"mllm"},{"id":"2605.02720","title":"Scientific Domain Knowledge Improves Vision-Language Fundus Models","created":"2026-05-04","cited_by_count":0,"area":"mllm"},{"id":"2605.10165","title":"Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.04922","title":"Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.15129","title":"EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP--OCT Pretraining","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.20913","title":"PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2606.22955","title":"Evo-RAD: Navigating Rare Retinal Disease Diagnosis via Self-Evolving Agentic Retrieval","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2607.09102","title":"Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imaging","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.18451","title":"CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25108","title":"OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis","created":"2026-07-27","cited_by_count":0,"area":"moe"},{"id":"2608.13455","title":"Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.25981","title":"FRAME: Separating sampling variation from performance disparities in medical image analysis","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.10333","title":"Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.32352","title":"EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"id":"2609.32559","title":"CFCH: Coarse-Fine Collaborative Hierarchical Learning for Anterior Segment Disease Analysis","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33158","title":"FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs","created":"2026-09-27","cited_by_count":0,"area":"mllm"}],"next_cursor":null}