{"total":53,"rows":[{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163,"area":null},{"id":"2502.20056","title":"Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation","created":"2025-02-27","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":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40,"area":"lr"},{"id":"2402.16040","title":"EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries","created":"2024-02-25","cited_by_count":35,"area":null},{"id":"2411.16778","title":"GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis","created":"2024-11-25","cited_by_count":29,"area":null},{"id":"2411.19378","title":"Libra: Leveraging Temporal Images for Biomedical Radiology Analysis","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2506.04353","title":"ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray Understanding","created":"2025-06-04","cited_by_count":20,"area":null},{"id":"2410.02331","title":"Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2408.16213","title":"M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation","created":"2024-08-29","cited_by_count":17,"area":"mllm"},{"id":"2411.05521","title":"SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark","created":"2024-11-08","cited_by_count":14,"area":null},{"id":"2503.13205","title":"MAP: Evaluation and Multi-Agent Enhancement of Large Language Models for Inpatient Pathways","created":"2025-03-17","cited_by_count":10,"area":"agents"},{"id":"2506.00235","title":"MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2404.02370","title":"Enhancing Human-Computer Interaction in Chest X-ray Analysis using Vision and Language Model with Eye Gaze Patterns","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2505.02830","title":"AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation","created":"2025-05-05","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2411.10937","title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry","created":"2024-11-17","cited_by_count":6,"area":"mllm"},{"id":"2604.02543","title":"Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation","created":"2026-04-02","cited_by_count":6,"area":"mllm"},{"id":"2504.10642","title":"SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging","created":"2025-04-14","cited_by_count":5,"area":"mllm"},{"id":"2506.22900","title":"MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering","created":"2025-06-28","cited_by_count":5,"area":null},{"id":"2604.00493","title":"A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation","created":"2026-04-01","cited_by_count":5,"area":"lr"},{"id":"2511.00504","title":"VinDr-CXR-VQA: A Visual Question Answering Dataset for Explainable Chest X-Ray Analysis with Multi-Task Learning","created":"2025-11-01","cited_by_count":3,"area":null},{"id":"2605.08146","title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2605.10286","title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2403.15456","title":"WoLF: Wide-scope Large Language Model Framework for CXR Understanding","created":"2024-03-19","cited_by_count":2,"area":"mllm"},{"id":"2409.07012","title":"Towards Predicting Temporal Changes in a Patient's Chest X-ray Images based on Electronic Health Records","created":"2024-09-11","cited_by_count":2,"area":null},{"id":"2504.09967","title":"Enhancing Multi-task Learning Capability of Medical Generalist Foundation Model via Image-centric Multi-annotation Data","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2508.12418","title":"Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2603.09512","title":"Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2605.09675","title":"CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents","created":"2026-05-10","cited_by_count":2,"area":"lr"},{"id":"2407.19517","title":"Evaluating LLMs for Text-to-SQL Generation With Complex SQL Workload","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2409.16183","title":"Expert-level vision-language foundation model for real-world radiology and comprehensive evaluation","created":"2024-09-24","cited_by_count":1,"area":"mllm"},{"id":"2411.19688","title":"SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks","created":"2024-11-29","cited_by_count":1,"area":"mllm"},{"id":"2507.08036","title":"Barriers in Integrating Medical Visual Question Answering into Radiology Workflows: A Scoping Review and Clinicians' Insights","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.02841","title":"A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering","created":"2025-08-04","cited_by_count":1,"area":"lr"},{"id":"2512.02485","title":"UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making","created":"2025-12-02","cited_by_count":1,"area":"mllm"},{"id":"2601.10020","title":"EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.04416","title":"Med-MMFL: A Multimodal Federated Learning Benchmark in Healthcare","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2605.15574","title":"MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.26691","title":"Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2509.20208","title":"Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2512.17213","title":"CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2601.13919","title":"HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.12843","title":"MMRad-22K: A Structured Multimodal Evidence Dataset for Chest X-ray Report Generation","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.15235","title":"MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.17140","title":"UCSF-PDGM-VQA: Visual Question Answering dataset for brain tumor MRI interpretation","created":"2026-05-16","cited_by_count":0,"area":"mllm"},{"id":"2606.25407","title":"Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.28329","title":"$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.30758","title":"CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretation","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.04842","title":"MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.13158","title":"TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.30027","title":"Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.01605","title":"Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}