{"total":93,"rows":[{"id":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338,"area":null},{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89,"area":"mllm"},{"id":"2410.13085","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","created":"2024-10-16","cited_by_count":85,"area":"mllm"},{"id":"2303.05977","title":"Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models","created":"2023-03-10","cited_by_count":58,"area":null},{"id":"2310.18652","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","created":"2023-10-28","cited_by_count":53,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37,"area":"mllm"},{"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":"2506.11147","title":"3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks","created":"2025-06-11","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2409.01437","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","created":"2024-09-02","cited_by_count":23,"area":null},{"id":"2401.02797","title":"PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging","created":"2024-01-05","cited_by_count":22,"area":"mllm"},{"id":"2410.04521","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration","created":"2024-10-06","cited_by_count":21,"area":"mllm"},{"id":"2302.09636","title":"Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning","created":"2023-02-19","cited_by_count":17,"area":null},{"id":"2311.09581","title":"DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation","created":"2023-11-16","cited_by_count":16,"area":null},{"id":"2307.12045","title":"Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-22","cited_by_count":15,"area":null},{"id":"2411.12783","title":"Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model","created":"2024-11-19","cited_by_count":15,"area":"mllm"},{"id":"2505.18915","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","created":"2025-05-25","cited_by_count":14,"area":"lr"},{"id":"2404.13039","title":"LaPA: Latent Prompt Assist Model For Medical Visual Question Answering","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2411.12195","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","created":"2024-11-19","cited_by_count":11,"area":null},{"id":"2508.05318","title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2402.08966","title":"Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays","created":"2024-02-14","cited_by_count":9,"area":"mllm"},{"id":"2506.02738","title":"Open-PMC-18M: A High-Fidelity Large Scale Medical Dataset for Multimodal Representation Learning","created":"2025-06-03","cited_by_count":9,"area":"mllm"},{"id":"2509.20146","title":"EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models","created":"2025-09-24","cited_by_count":9,"area":"mllm"},{"id":"2309.11080","title":"Visual Question Answering in the Medical Domain","created":"2023-09-20","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":"2505.15401","title":"Visual Question Answering on Multiple Remote Sensing Image Modalities","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2512.01922","title":"Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding","created":"2025-12-01","cited_by_count":6,"area":"mllm"},{"id":"2210.00220","title":"A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2401.06400","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2404.16192","title":"Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering","created":"2024-04-24","cited_by_count":5,"area":"mllm"},{"id":"2410.06420","title":"ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments","created":"2024-10-08","cited_by_count":5,"area":"mllm"},{"id":"2410.14991","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2503.18213","title":"A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives","created":"2025-03-23","cited_by_count":5,"area":null},{"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":"2401.13081","title":"Free Form Medical Visual Question Answering in Radiology","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2402.09677","title":"Prompt-based Personalized Federated Learning for Medical Visual Question Answering","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2507.07902","title":"MIRA: A Novel Framework for Fusing Modalities in Medical RAG","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2304.00436","title":"Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2410.16239","title":"MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2505.16624","title":"Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2510.13856","title":"Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA","created":"2025-10-12","cited_by_count":3,"area":"rag"},{"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":"2511.21339","title":"SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2306.17675","title":"Multimodal Prompt Retrieval for Generative Visual Question Answering","created":"2023-06-30","cited_by_count":2,"area":"mllm"},{"id":"2405.01583","title":"MediFact at MEDIQA-M3G 2024: Medical Question Answering in Dermatology with Multimodal Learning","created":"2024-04-27","cited_by_count":2,"area":null},{"id":"2502.05928","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2503.18536","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","created":"2025-03-24","cited_by_count":2,"area":"diffusion"},{"id":"2505.19624","title":"Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat","created":"2025-05-26","cited_by_count":2,"area":"mllm"},{"id":"2601.18240","title":"V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering","created":"2026-01-26","cited_by_count":2,"area":"mllm"},{"id":"2605.01911","title":"SurgCheck: Do Vision-Language Models Really Look at Images in Surgical VQA?","created":"2026-05-03","cited_by_count":2,"area":"mllm"},{"id":"2606.15647","title":"Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2405.11145","title":"Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2410.09428","title":"Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets","created":"2024-10-12","cited_by_count":1,"area":"distill"},{"id":"2410.16662","title":"Visual Question Answering in Ophthalmology: A Progressive and Practical Perspective","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2410.17484","title":"Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2412.10337","title":"Generative AI in Medicine","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2412.15925","title":"MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Classification and Detection","created":"2024-12-20","cited_by_count":1,"area":"mllm"},{"id":"2503.03278","title":"Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions","created":"2025-03-05","cited_by_count":1,"area":"mllm"},{"id":"2504.03135","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2507.04333","title":"Computed Tomography Visual Question Answering with Cross-modal Feature Graphing","created":"2025-07-06","cited_by_count":1,"area":null},{"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":"2510.02328","title":"AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2510.08791","title":"Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.22803","title":"MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering","created":"2025-10-26","cited_by_count":1,"area":null},{"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":"2601.01363","title":"A unified multimodal understanding and generation model for cross-disciplinary scientific research","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2603.15134","title":"Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation","created":"2026-03-16","cited_by_count":1,"area":"mllm"},{"id":"2604.01310","title":"Sparse Spectral LoRA: Routed Experts for Medical VLMs","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2605.23629","title":"DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2206.14397","title":"Fair Machine Learning in Healthcare: A Review","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2303.04388","title":"Interpretable Visual Question Answering Referring to Outside Knowledge","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2307.09886","title":"A reinforcement learning approach for VQA validation: an application to diabetic macular edema grading","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2505.16209","title":"MedCFVQA: A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.12036","title":"Q-FSRU: Quantum-Augmented Frequency-Spectral Fusion for Medical Visual Question Answering","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.23899","title":"Q-FSRU: Quantum-Augmented Frequency-Spectral For Medical Visual Question Answering","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2511.01357","title":"CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering","created":"2025-11-03","cited_by_count":0,"area":"ssm"},{"id":"2603.16372","title":"InViC: Intent-aware Visual Cues for Medical Visual Question Answering","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.18313","title":"Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.24159","title":"EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.03269","title":"Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16583","title":"Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?","created":"2026-06-15","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":"2607.12048","title":"An Empirical Analysis of Continual Learning for Heterogeneous Medical Visual Question Answering","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.15241","title":"Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.17834","title":"Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.18833","title":"EVADE: Evidence-Verified Agentic Diagnosis with Escape","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.22363","title":"Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.00959","title":"Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}