Introduces the first large-scale multimodal benchmark MedLayXPlain-122K showing medical VLMs suffer significant lay-register degradation while general VLMs lack clinical precision.
arXiv preprint arXiv:2510.08668 (2025)
33 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
33
Pith papers citing it
1
external citations · external index
citation-role summary
background 2
baseline 2
citation-polarity summary
years
2026 33representative citing papers
MedHorizon benchmark reveals current multimodal LLMs achieve only 41.1% accuracy on long medical videos due to failures in sparse evidence retrieval and procedural reasoning.
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
CheXpercept is a sequential multi-level perception benchmark showing VLMs perform adequately only on coarse lesion detection in chest X-rays while degrading sharply on finer tasks, with medical VLMs offering no advantage over general models.
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
Introduces MedReCo-DB dataset of 690k+ images and entity-aware models MedReCo/MedReCo-VLM that improve reference retrieval and comparative change interpretation in radiology across multiple centers and modalities.
CardioLens is a leakage-resistant CMR testbed of 473k slices and 13k QA pairs showing current MLLMs exhibit a large clinical reality gap with category-collapse failures on real workflows.
JMed48k is a new benchmark of Japanese healthcare licensing exams used to evaluate 21 VLMs, with a paired image-removal audit revealing large differences in how models and professions benefit from visual content.
DermAgent orchestrates seven vision-language tools in a Plan-Execute-Reflect loop with dual-modality retrieval from 413k cases and a critic module to outperform GPT-4o by 17.6% in zero-shot dermatological diagnosis accuracy.
Medical MLLMs degrade on image classification due to four failure modes in visual representation quality, connector projection fidelity, LLM comprehension, and semantic mapping alignment, quantified by feature probing on 14 models across 3 datasets.
Astra generates style-consistent multi-organ CT reports that generalize across institutions via report harmonization plus GRPO reinforcement learning, improving clinical drafting and enabling synthetic pretraining.
MedStreamBench integrates 22 medical datasets into 5,419 QA instances across retrospective, present, future, and proactive temporal settings to evaluate streaming and proactive medical video understanding.
ViToS uses dual-stream RL with cross-feedback optimization to prune medical image tokens to 77% length while reporting 108.27% and 104.16% relative performance on two 7B VLMs across seven benchmarks.
AtomiMed is a new modality-agnostic evaluation framework for medical report generation that decomposes reports into hierarchical atomic clinical facts and applies agentic cross-verification to achieve higher correlation with radiologist judgments than n-gram metrics.
Dementia-Agents is a three-step multi-agent framework using a data agent, five expert agents, and a coordinator to improve real-world dementia staging and phenotyping on 1,066 patients.
The paper diagnoses Template Collapse in 3D medical VLMs for CT reports and introduces CLarGen, a decoupled detection-plus-synthesis framework that raises macro-F1 from 0.189 to 0.487.
SurgOnAir introduces a streaming vision-language model trained on a hierarchical surgical dataset to generate real-time, multi-level narrations with explicit transition tokens.
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
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.
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.
On 20 real wound images and 240 clinician-scored decisions, ChatGPT (72.5%) and Claude (62%) substantially outperform medical VLMs HuluMed (40%) and MedGemma (18-26%).
Hierarchical clinical-reasoning SFT plus counterfactual GRPO yields SoTA diagnostic accuracy for multimodal LLMs on gastrointestinal endoscopy benchmarks.
View-PNDF detects and selectively fine-tunes view-specific neurons for consistent multi-view chest X-ray report generation, followed by LLM consolidation of reports.
Releases open medical LVLMs trained on a quality-filtered multimodal dataset, introduces CareQA-Vision benchmark from exams, reports performance gains over baselines, and flags adversarial vulnerabilities.
citing papers explorer
-
MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models
Introduces the first large-scale multimodal benchmark MedLayXPlain-122K showing medical VLMs suffer significant lay-register degradation while general VLMs lack clinical precision.
-
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
MedHorizon benchmark reveals current multimodal LLMs achieve only 41.1% accuracy on long medical videos due to failures in sparse evidence retrieval and procedural reasoning.
-
MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical Benchmark
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
-
CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-rays
CheXpercept is a sequential multi-level perception benchmark showing VLMs perform adequately only on coarse lesion detection in chest X-rays while degrading sharply on finer tasks, with medical VLMs offering no advantage over general models.
-
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
-
A Vision-language Framework for Comparative Reasoning in Radiology
Introduces MedReCo-DB dataset of 690k+ images and entity-aware models MedReCo/MedReCo-VLM that improve reference retrieval and comparative change interpretation in radiology across multiple centers and modalities.
-
CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations
CardioLens is a leakage-resistant CMR testbed of 473k slices and 13k QA pairs showing current MLLMs exhibit a large clinical reality gap with category-collapse failures on real workflows.
-
JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
JMed48k is a new benchmark of Japanese healthcare licensing exams used to evaluate 21 VLMs, with a paired image-removal audit revealing large differences in how models and professions benefit from visual content.
-
DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making
DermAgent orchestrates seven vision-language tools in a Plan-Execute-Reflect loop with dual-modality retrieval from 413k cases and a critic module to outperform GPT-4o by 17.6% in zero-shot dermatological diagnosis accuracy.
-
Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
Medical MLLMs degrade on image classification due to four failure modes in visual representation quality, connector projection fidelity, LLM comprehension, and semantic mapping alignment, quantified by feature probing on 14 models across 3 datasets.
-
Astra: a generalizable report generation foundation model for 3D computed tomography
Astra generates style-consistent multi-organ CT reports that generalize across institutions via report harmonization plus GRPO reinforcement learning, improving clinical drafting and enabling synthetic pretraining.
-
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding
MedStreamBench integrates 22 medical datasets into 5,419 QA instances across retrospective, present, future, and proactive temporal settings to evaluate streaming and proactive medical video understanding.
-
Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
ViToS uses dual-stream RL with cross-feedback optimization to prune medical image tokens to 77% length while reporting 108.27% and 104.16% relative performance on two 7B VLMs across seven benchmarks.
-
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation
AtomiMed is a new modality-agnostic evaluation framework for medical report generation that decomposes reports into hierarchical atomic clinical facts and applies agentic cross-verification to achieve higher correlation with radiologist judgments than n-gram metrics.
-
Dementia-Agents: A Multi-Modal Multi-Agent System for Dementia Staging and Phenotyping
Dementia-Agents is a three-step multi-agent framework using a data agent, five expert agents, and a coordinator to improve real-world dementia staging and phenotyping on 1,066 patients.
-
Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation
The paper diagnoses Template Collapse in 3D medical VLMs for CT reports and introduces CLarGen, a decoupled detection-plus-synthesis framework that raises macro-F1 from 0.189 to 0.487.
-
SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary
SurgOnAir introduces a streaming vision-language model trained on a hierarchical surgical dataset to generate real-time, multi-level narrations with explicit transition tokens.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
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.
-
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.
-
Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound images
On 20 real wound images and 240 clinician-scored decisions, ChatGPT (72.5%) and Claude (62%) substantially outperform medical VLMs HuluMed (40%) and MedGemma (18-26%).
-
Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
Hierarchical clinical-reasoning SFT plus counterfactual GRPO yields SoTA diagnostic accuracy for multimodal LLMs on gastrointestinal endoscopy benchmarks.
-
Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation
View-PNDF detects and selectively fine-tunes view-specific neurons for consistent multi-view chest X-ray report generation, followed by LLM consolidation of reports.
-
Aloe-Vision: Robust Vision-Language Models for Healthcare
Releases open medical LVLMs trained on a quality-filtered multimodal dataset, introduces CareQA-Vision benchmark from exams, reports performance gains over baselines, and flags adversarial vulnerabilities.
-
E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis
E-MRL trains VLMs via RL on a diagnosis-localization-verification MDP with a novel cross-view consistency reward to ground 3D tumor reports in verifiable CT slices.
-
Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports
Lightweight metrics trained on Qwen3-8B and MedGemma-4B using synthetic pairs outperform larger medical LLMs at distinguishing clinical significance in radiology reports while balancing discrimination and robustness.
-
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
A GRPO-based RL framework with probabilistic risk minimization, disagreement-aware synergy rewards, and entropy-guided sampling enables instance-level tool selection that closes the single-oracle risk gap on medical benchmarks.
-
VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
VIHD detects hallucinations in medical MLLMs via visual dependency probing, token masking intervention, and calibrated semantic entropy on VQA benchmarks.
-
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
TIF-GRPO uses integral feedback on pseudo-temporal trajectories to regulate anatomy-aware rewards in RL for clinical faithfulness in volumetric CT analysis.
-
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
ECHO introduces one-step block diffusion via Direct Conditional Distillation and Response-Asymmetric Diffusion to generate chest X-ray reports faster than autoregressive models while improving clinical metrics.
-
APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
Presents APRIL-MedSeg, a modular YAML-configurable toolbox for 2D medical image segmentation integrating semi-supervised, domain adaptation, distillation, weakly supervised, text-guided, and foundation model paradigms with unified dataset and deployment interfaces.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
-
Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
The paper describes Baichuan-M4, a coordinated medical agent system that reports leading scores across static knowledge, dynamic consultation, long-context memory, retrieval, OCR, and multimodal tasks with a 3.3% hallucination rate.