VQA-Rad

Dataset Card for VQA-RAD Dataset Description VQA-RAD is a dataset of question-answer pairs on radiology images. The dataset is intended to be used for training and testing Medical Visual Question Answering (VQA) systems. The dataset includes both open-ended questions and binary "yes/no" questions. The dataset is built

Papers using VQA-Rad (26)

Capabilities Of GPT-5 On Multimodal Medical Reasoning2025 · 10 citesScalable Training of Spatially Grounded 2D Vision-Language Models for Radiology2026Benchmarking GPT-5 For Zero-shot Multimodal Medical Reasoning In Radiology And Radiation Oncology2025 · 3 citesA Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy2026Benchmarking The Thinking Mode Of Multimodal Large Language Models In Clinical Tasks2025 · 1 citesWasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering2026Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA2026InViC: Intent-aware Visual Cues for Medical Visual Question Answering2026VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs2026Robust Pre-Training of Medical Vision-and-Language Models with Domain-Invariant Multi-Modal Masked Reconstruction2026Decoupling Vision and Language: Codebook Anchored Visual Adaptation2026CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering2025HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models2025Llada-medv: Exploring Large Language Diffusion Models For Biomedical Image Understanding2025How Far Have Medical Vision-language Models Come? A Comprehensive Benchmarking Study2025Medvqa-tree: A Multimodal Reasoning And Retrieval Framework For Sarcopenia Prediction2025Test-time Warmup For Multimodal Large Language Models2025Q-FSRU: Quantum-augmented Frequency-spectral Fusion For Medical Visual Question Answering2025MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering2021 · 9 citesMedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine2024 · 8 citesRAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training2023 · 5 citesMedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale2024 · 2 citesMulti-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training2021 · 1 citesLaPA: Latent Prompt Assist Model For Medical Visual Question Answering2024 · 1 citesFusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering2024 · 1 citesMMBERT: Multimodal BERT Pretraining for Improved Medical VQA2021