Tao Tan

Synthesized breast MRIs can now better mimic real-world lesion complexity thanks to a diffusion model that explicitly handles multi-scale features and heterogeneous enhancement.

Breast cancer risk prediction from MRI just got a whole lot faster and more interpretable, thanks to a novel 2.5D approach that beats both 2D and 3D models.

Saliency detection in remote sensing gets a huge speed boost with ORSIFlow, a rectified flow approach that leaps ahead of slower diffusion-based methods.

Stop predicting the future, start predicting *change*: $Δ$VLA guides robotic action by modeling how world knowledge *varies* under actions, not by forecasting absolute future states.