A chest X-ray contrastive model that masks false-negative image-report pairs using adaptive similarity thresholds, then distills two rule-specific teachers, reaches 0.850 mean zero-shot AUC across five benchmarks.
Contrastive learning of medical visual representations from paired images and text
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
Injecting multi-expert anatomy/lesion segmentation priors into vision–language alignment and calibrating text attention with lesion masks yields broad CT diagnosis plus specialist-level tumor performance and lesion grounding.
GLINT introduces sparsely gated alignment and dense feature regularization on top of DINOv3 and V-JEPA encoders to enable query-specific zero-shot grounding and segmentation in 2D CXR and 3D CT.
CLEF, a long-context EEG foundation model using 3D multitaper spectrograms and contrastive alignment with reports and EHR, beats prior models on 229 of 234 clinical tasks and raises mean AUROC from 0.65 to 0.74.
MUST supervision—LLM-distilled diagnostic labels plus two-stage ubiquitous training—lets a 33M-parameter 3D ResNet-18 reach 84.8 zero-shot AUC on CT-RATE in 24 GPU-hours and transfer across institutions and MRI.
A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.
citing papers explorer
-
SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis
A chest X-ray contrastive model that masks false-negative image-report pairs using adaptive similarity thresholds, then distills two rule-specific teachers, reaches 0.850 mean zero-shot AUC across five benchmarks.
-
Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy
Injecting multi-expert anatomy/lesion segmentation priors into vision–language alignment and calibrating text attention with lesion masks yields broad CT diagnosis plus specialist-level tumor performance and lesion grounding.
-
GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
GLINT introduces sparsely gated alignment and dense feature regularization on top of DINOv3 and V-JEPA encoders to enable query-specific zero-shot grounding and segmentation in 2D CXR and 3D CT.
-
CLEF: EEG Foundation Model for Learning Clinical Semantics
CLEF, a long-context EEG foundation model using 3D multitaper spectrograms and contrastive alignment with reports and EHR, beats prior models on 229 of 234 clinical tasks and raises mean AUROC from 0.65 to 0.74.
-
GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training
MUST supervision—LLM-distilled diagnostic labels plus two-stage ubiquitous training—lets a 33M-parameter 3D ResNet-18 reach 84.8 zero-shot AUC on CT-RATE in 24 GPU-hours and transfer across institutions and MRI.
-
Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification
A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.
- EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models