MatMMExtract pipeline creates MatSciFig dataset of 391k annotated materials science figure panels and MaterialScope detection dataset with high accuracy.
Scientific Data6, 317 (2019)
21 Pith papers cite this work, alongside 1,621 external citations. Polarity classification is still indexing.
21
Pith papers citing it
1,621
external citations · OpenAlex
representative citing papers
SAS reveals that medical images retain richer structural information than paired clinical reports in VLMs, an asymmetry hidden from symmetric metrics, with strongest correlation to retrieval performance.
EchoVQA is the first large-scale VQA dataset for echocardiography spanning high- and low-quality images across views, with acquisition guidance questions, paired with a low-parameter multimodal prompt model that reports SOTA on several benchmarks.
Diffusion LM matches AR performance on medical VQA, runs 3.5-4.4x faster, and enables bidirectional infilling for interactive radiology report drafting.
TAVR-VLM introduces Risk-Conditioned Causal Grounding Attention to achieve SOTA AUROC 0.896, CIDEr 0.936, and 8.1% hallucination rate on a 1,482-patient TAVR cohort.
LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
OPAL learns optimal smooth labeling policies from ML uncertainty scores to enable low-variance prediction-assisted inference with finite-sample coverage guarantees.
DIVE improves in-context vector distillation for medical report generation via decisive-token supervision on pathology terms and EOS plus state-conditioned dynamic steering, achieving top BLEU-4, ROUGE-L and RadGraph F1 on MIMIC-CXR and CheXpert Plus.
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.
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
-
Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature
MatMMExtract pipeline creates MatSciFig dataset of 391k annotated materials science figure panels and MaterialScope detection dataset with high accuracy.
-
Beyond Symmetric Alignment: Spectral Diagnostics of Modality Imbalance in Vision-Language Models in the Medical Domain
SAS reveals that medical images retain richer structural information than paired clinical reports in VLMs, an asymmetry hidden from symmetric metrics, with strongest correlation to retrieval performance.
-
EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound
EchoVQA is the first large-scale VQA dataset for echocardiography spanning high- and low-quality images across views, with acquisition guidance questions, paired with a low-parameter multimodal prompt model that reports SOTA on several benchmarks.
-
Discrete Diffusion Language Models for Interactive Radiology Report Drafting
Diffusion LM matches AR performance on medical VQA, runs 3.5-4.4x faster, and enables bidirectional infilling for interactive radiology report drafting.
-
TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation
TAVR-VLM introduces Risk-Conditioned Causal Grounding Attention to achieve SOTA AUROC 0.896, CIDEr 0.936, and 8.1% hallucination rate on a 1,482-patient TAVR cohort.
-
From `May' to `Is': Certainty Distortion in Language Model Rewriting
LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
-
Optimized Labeling Resource Allocation for Prediction-Assisted Inference via OPAL
OPAL learns optimal smooth labeling policies from ML uncertainty scores to enable low-variance prediction-assisted inference with finite-sample coverage guarantees.
-
Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
DIVE improves in-context vector distillation for medical report generation via decisive-token supervision on pathology terms and EOS plus state-conditioned dynamic steering, achieving top BLEU-4, ROUGE-L and RadGraph F1 on MIMIC-CXR and CheXpert Plus.
-
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.