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.
Title resolution pending
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
verdicts
UNVERDICTED 13representative citing papers
Fine-tuned MLLMs achieve competitive skeletal landmark localization on synthetic and real X-ray datasets compared to deep learning baselines and demonstrate reasoning for sequential C-arm navigation.
Mean pooling and multi-window RGB encoding optimize vision-language performance on CT enterography, with retrieval-augmented generation substantially improving automated report severity accuracy over fine-tuning alone.
MediSyn is a generalist latent diffusion model that synthesizes text-guided medical images across multiple specialties and modalities from public data and improves downstream classifiers in low-data settings.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
A sample-difficulty decorrelation method that attenuates age-dependent confounding in radiology classification by modeling label-conditioned difficulty trends and applying robust Huber-weighted affinity penalties scaled by an Age Coverage Score.
A worst-group equalized odds regularizer targets extreme subgroup deviations in true and false positive rates to improve multi-attribute fairness in medical imaging while preserving AUC.
RadGenome-Anatomy is a large-scale chest radiograph dataset with anatomy labels obtained by projecting 3D CT masks into 2D radiographic space for 210 structures in 25,692 studies.
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.
Lingshu is a medical-specialized multimodal LLM that outperforms prior open-source models on multimodal QA, text QA, and report generation after training on a large curated dataset of medical knowledge.
ProtoCLIP improves zero-shot chest X-ray classification in CLIP models by 2-10 AUC points via curated data and prototype-aligned distillation, reaching 0.94 AUC for pneumothorax on VinDr-CXR.
LLaMA-XR fine-tunes LLaMA 3.1 with QLoRA on DenseNet-121 embeddings to generate radiology reports from chest X-rays, reporting ROUGE-L of 0.433 and METEOR of 0.336 on the IU X-ray benchmark.
citing papers explorer
-
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.
-
Autonomous Skeletal Landmark Localization towards Agentic C-Arm Control
Fine-tuned MLLMs achieve competitive skeletal landmark localization on synthetic and real X-ray datasets compared to deep learning baselines and demonstrate reasoning for sequential C-arm navigation.
-
Representation geometry shapes task performance in vision-language modeling for CT enterography
Mean pooling and multi-window RGB encoding optimize vision-language performance on CT enterography, with retrieval-augmented generation substantially improving automated report severity accuracy over fine-tuning alone.
-
A Generalist Model for Diverse Text-Guided Medical Image Synthesis
MediSyn is a generalist latent diffusion model that synthesizes text-guided medical images across multiple specialties and modalities from public data and improves downstream classifiers in low-data settings.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
A sample-difficulty decorrelation method that attenuates age-dependent confounding in radiology classification by modeling label-conditioned difficulty trends and applying robust Huber-weighted affinity penalties scaled by an Age Coverage Score.
-
Worst-Group Equalized Odds Regularization for Multi-Attribute Fair Medical Image Classification
A worst-group equalized odds regularizer targets extreme subgroup deviations in true and false positive rates to improve multi-attribute fairness in medical imaging while preserving AUC.
-
RadGenome-Anatomy: A Large-Scale Anatomy-Labeled Chest Radiograph Dataset via Physically Grounded Volumetric Projection
RadGenome-Anatomy is a large-scale chest radiograph dataset with anatomy labels obtained by projecting 3D CT masks into 2D radiographic space for 210 structures in 25,692 studies.
-
AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
-
CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.
-
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Lingshu is a medical-specialized multimodal LLM that outperforms prior open-source models on multimodal QA, text QA, and report generation after training on a large curated dataset of medical knowledge.
-
ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification
ProtoCLIP improves zero-shot chest X-ray classification in CLIP models by 2-10 AUC points via curated data and prototype-aligned distillation, reaching 0.94 AUC for pneumothorax on VinDr-CXR.
-
LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning
LLaMA-XR fine-tunes LLaMA 3.1 with QLoRA on DenseNet-121 embeddings to generate radiology reports from chest X-rays, reporting ROUGE-L of 0.433 and METEOR of 0.336 on the IU X-ray benchmark.