MRG-LLM creates image-specific prompts by applying learned shifts and scales to a set of base prompts, improving automated radiology report generation on IU X-ray and MIMIC-CXR.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Large Language Models for Medical Report Generation via Customized Prompt Tuning
MRG-LLM creates image-specific prompts by applying learned shifts and scales to a set of base prompts, improving automated radiology report generation on IU X-ray and MIMIC-CXR.