Yipei Wang

Continual pretraining a ViT encoder with LoRA on prostate MRI segmentation significantly improves downstream task alignment and performance, particularly for segmentation tasks, by inducing targeted representational shifts.

Actively repelling uncertain features during representation learning slashes extreme segmentation errors in ambiguous anatomical boundaries by 22x, even without sacrificing overall accuracy.

Suppressing certain clinical covariates can actually improve the predictive power of prostate MRI grading models, revealing hidden dependencies that could mislead performance assessments.