GTA-Net applies cooperative game theory via BinaryGameAligner and Disease-Aware Ternary Aligner on Swin+LoRA backbones to enforce region-word and disease consistency in chest X-ray reports, reporting SOTA metrics on CheXpertPlus and IU-XRay.
A survey of deep learning-based radiology report generation using multimodal data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
citing papers explorer
-
GTA-Net: Cooperative Game Theory for Vision-Language Alignment in Chest X-Ray Report Generation
GTA-Net applies cooperative game theory via BinaryGameAligner and Disease-Aware Ternary Aligner on Swin+LoRA backbones to enforce region-word and disease consistency in chest X-ray reports, reporting SOTA metrics on CheXpertPlus and IU-XRay.
-
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.