NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
hub Mixed citations
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
Mixed citation behavior. Most common role is background (60%).
35
Pith papers citing it
Background
60% of classified citations
abstract
Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery by leveraging artificial intelligence to interpret and answer questions based on medical images. In this study, we reframe the problem of MedVQA as a generation task that naturally follows the human-machine interaction and propose a generative-based model for medical visual understanding by aligning visual information from a pre-trained vision encoder with a large language model. We establish a scalable pipeline to construct a large-scale medical visual question-answering dataset, named PMC-VQA, which contains 227k VQA pairs of 149k images that cover various modalities or diseases. We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef-2019, significantly outperforming existing MedVQA models in generating relevant, accurate free-form answers. In addition, we propose a test set that has undergone manual verification, which is significantly more challenging, serving to better monitor the development of generative MedVQA methods. To facilitate comprehensive evaluation and comparison, we have maintained a leaderboard at https://paperswithcode.com/paper/pmc-vqa-visual-instruction-tuning-for-medical, offering a centralized resource for tracking progress and benchmarking state-of-the-art approaches. The PMC-VQA dataset emerges as a vital resource for the field of research, and the MedVInT presents a significant breakthrough in the area of MedVQA.
hub tools
citation-role summary
background 7
dataset 3
citation-polarity summary
representative citing papers
DeepTumorVQA is a new stage-wise 3D CT VQA benchmark showing that quantitative measurement is the main failure point for current medical VLMs and that tool augmentation substantially improves later reasoning stages.
MedFlowBench evaluates VLM agents on full radiology and pathology studies by requiring both task answers and verifiable evidence like key slices and regions of interest, revealing that answer-only scores overestimate performance.
Fetal-Gauge benchmark shows state-of-the-art vision-language models reach only 55% accuracy on fetal ultrasound tasks, well below clinical needs and highlighting the requirement for domain-adapted models.
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
CheXthought supplies large-scale expert chain-of-thought reasoning and synchronized visual attention data for chest X-rays to train more accurate and interpretable clinical vision-language models.
X-PCR is a new benchmark of 26,415 images and 177,868 expert VQA pairs that evaluates MLLMs on six-stage progressive reasoning and cross-modality integration in ophthalmology.
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
MedExpMem lets VLM diagnostic agents store and retrieve experience from past failures as pairwise differential notes, producing up to 7% accuracy gains on a multi-subspecialty radiology benchmark.
Contrastive pretraining on mammography atlas image-text pairs improves BI-RADS classification F1 by 1-14% especially in low-label regimes, outperforming equivalent numbers of direct labels in some settings.
Introduces BanglaMedVQA dataset of clinically validated image-question-answer pairs and benchmarks foundation models, finding substantially lower performance than on English MedVQA especially on diagnostic questions.
Self-verification in medical VQA creates a verification mirage where verifiers exhibit high error and agreement bias on wrong answers, with reliability strongly conditioned on task type.
RadThinking releases a large longitudinal CT VQA dataset stratified into foundation perception questions, single-rule reasoning questions, and compositional multi-step chains grounded in clinical reporting standards for cancer screening.
MedVIGIL provides a 300-case evaluation suite with 2556 probes that measures silent failures in medical VLMs under broken evidence, showing the best model at 69.2 on the composite score versus a human radiologist at 83.3.
MoR lets clients train local reward models on private preferences and uses a learned Mixture-of-Rewards with GRPO on the server to align a shared base VLM without exchanging parameters, architectures, or raw data.
DCI unifies backdoor adjustment and instrumental variable learning in MedVQA to extract deconfounded representations, yielding better out-of-distribution performance on SLAKE, VQA-RAD and similar benchmarks.
MedRCube is a new fine-grained evaluation framework that benchmarks 33 MLLMs on medical imaging, ranks Lingshu-32B highest, and finds a significant positive link between shortcut behaviors and diagnostic performance.
DCP-PD improves macro F1 scores on CT report generation benchmarks and introduces a hierarchical location-aware evaluation protocol that reveals ongoing challenges in pathology spatial grounding.
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
Chain-of-thought underperforms direct answering in medical VQA due to a perception bottleneck, but ROI cues and textual grounding interventions can improve results and reverse the gap.
One Tokenizer achieves zero-gap multimodal integration by mapping all inputs to a unified token vocabulary, allowing native LLMs to perform deep cross-modal reasoning without modular encoders or fusion layers, and outperforming encoder-based baselines on DNA-text tasks.
FPBench evaluates 20 MLLMs across 8 fingerprint tasks on 7 datasets and shows fine-tuning vision and language encoders improves performance by 7-39%.
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
citing papers explorer
-
NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding
NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
-
DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents
DeepTumorVQA is a new stage-wise 3D CT VQA benchmark showing that quantitative measurement is the main failure point for current medical VLMs and that tool augmentation substantially improves later reasoning stages.
-
MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows
MedFlowBench evaluates VLM agents on full radiology and pathology studies by requiring both task answers and verifiable evidence like key slices and regions of interest, revealing that answer-only scores overestimate performance.
-
FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound
Fetal-Gauge benchmark shows state-of-the-art vision-language models reach only 55% accuracy on fetal ultrasound tasks, well below clinical needs and highlighting the requirement for domain-adapted models.
-
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
-
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
-
CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation
CheXthought supplies large-scale expert chain-of-thought reasoning and synchronized visual attention data for chest X-rays to train more accurate and interpretable clinical vision-language models.
-
X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis
X-PCR is a new benchmark of 26,415 images and 177,868 expert VQA pairs that evaluates MLLMs on six-stage progressive reasoning and cross-modality integration in ophthalmology.
-
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
-
MedExpMem: Adapting Experience Memory for Differential Diagnosis
MedExpMem lets VLM diagnostic agents store and retrieve experience from past failures as pairwise differential notes, producing up to 7% accuracy gains on a multi-subspecialty radiology benchmark.
-
MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification
Contrastive pretraining on mammography atlas image-text pairs improves BI-RADS classification F1 by 1-14% especially in low-label regimes, outperforming equivalent numbers of direct labels in some settings.
-
How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking
Introduces BanglaMedVQA dataset of clinically validated image-question-answer pairs and benchmarks foundation models, finding substantially lower performance than on English MedVQA especially on diagnostic questions.
-
Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
Self-verification in medical VQA creates a verification mirage where verifiers exhibit high error and agreement bias on wrong answers, with reliability strongly conditioned on task type.
-
RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology
RadThinking releases a large longitudinal CT VQA dataset stratified into foundation perception questions, single-rule reasoning questions, and compositional multi-step chains grounded in clinical reporting standards for cancer screening.
-
MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
MedVIGIL provides a 300-case evaluation suite with 2556 probes that measures silent failures in medical VLMs under broken evidence, showing the best model at 69.2 on the composite score versus a human radiologist at 83.3.
-
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models
MoR lets clients train local reward models on private preferences and uses a learned Mixture-of-Rewards with GRPO on the server to align a shared base VLM without exchanging parameters, architectures, or raw data.
-
Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA
DCI unifies backdoor adjustment and instrumental variable learning in MedVQA to extract deconfounded representations, yielding better out-of-distribution performance on SLAKE, VQA-RAD and similar benchmarks.
-
MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging
MedRCube is a new fine-grained evaluation framework that benchmarks 33 MLLMs on medical imaging, ranks Lingshu-32B highest, and finds a significant positive link between shortcut behaviors and diagnostic performance.
-
Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance
DCP-PD improves macro F1 scores on CT report generation benchmarks and introduces a hierarchical location-aware evaluation protocol that reveals ongoing challenges in pathology spatial grounding.
-
Improving Medical VQA through Trajectory-Aware Process Supervision
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
-
Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
Chain-of-thought underperforms direct answering in medical VQA due to a perception bottleneck, but ROI cues and textual grounding interventions can improve results and reverse the gap.
-
Mind the Gap No More: Achieving Zero-Gap Multimodal Integration via One Tokenizer
One Tokenizer achieves zero-gap multimodal integration by mapping all inputs to a unified token vocabulary, allowing native LLMs to perform deep cross-modal reasoning without modular encoders or fusion layers, and outperforming encoder-based baselines on DNA-text tasks.
-
FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis
FPBench evaluates 20 MLLMs across 8 fingerprint tasks on 7 datasets and shows fine-tuning vision and language encoders improves performance by 7-39%.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation
BiomedAP improves robustness of biomedical VLMs to prompt variations using gated cross-modal fusion and dual-anchor constraints, outperforming baselines on 11 benchmarks.
-
RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding
RoiMAM integrates a training-free ROI Generation Module with Semantic Selective Suppression and a Text Prompt Enhancer to produce a compact VLM that reports 2 percent and 4.6 percent accuracy gains on SLAKE and PMC-VQA at less than 20 percent the size of MedVInT-TD.
-
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
LiteMedCoT-VL distills chain-of-thought from a 235B model to 2B VLMs via LoRA, reaching 64.9% accuracy on PMC-VQA and beating a 4B zero-shot baseline by 11 points.
-
Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs
A Medical Entity Tree organizes medical knowledge to engineer higher-quality training data that boosts general MLLMs on medical benchmarks.
-
MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
MedLVR interleaves latent visual reasoning segments in autoregressive decoding and uses two-stage training to raise average medical VQA accuracy from 48.3% to 53.4% over a Qwen2.5-VL-7B backbone on OmniMedVQA and five other benchmarks.
-
Online In-Context Distillation for Low-Resource Vision Language Models
Online In-Context Distillation lets small VLMs gain up to 33% performance with as little as 4% teacher annotations by distilling knowledge through dynamic in-context demonstrations at inference.
-
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
MedXIAOHE is a medical MLLM that claims state-of-the-art benchmark performance through specialized pretraining to cover long-tail diseases and RL-based reasoning training.
-
A Survey on Knowledge Distillation of Large Language Models
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.
-
A Survey on Multimodal Large Language Models
This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.
- JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
- MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution