Fix acceleration wording; cite UNIFORM, vSHARP, and DIRECT

README.md

@@ -25,7 +25,7 @@ undersampled multi-coil MRI across diverse anatomical sites and contrasts, built
 ![UNIFORM training and inference pipeline](uniform_figure1_pipeline.png)
 
 *Figure 1 (MIDL 2025): one vSHARP model trained on fastMRI brain / knee / prostate and
-CMRxRecon cardiac data; evaluated at \(R\in\{2,4,6,8\}\); zero-shot SSL on breast in the paper.*
+CMRxRecon cardiac data; evaluated at **2×, 4×, 6×, and 8×** acceleration; zero-shot SSL on breast in the paper.*
 
 ## What is in this repo?
 
@@ -98,6 +98,8 @@ masking:
 
 ## Citation
 
+If you use this model, please cite UNIFORM, vSHARP, and the DIRECT toolkit.
+
 ```bibtex
 @inproceedings{Yiasemis_UNIFORM,
   title     = {{UNIFORM}: A Unified Deep Learning Framework for Multi-organ and Multi-contrast {MRI} Reconstruction},