Yao Xu

To develop a clinically oriented framework for patient-specific 3D dose prediction in head-and-neck radiotherapy, emphasizing DVH-consistent performance for target coverage and OAR sparing.

To advance sparse-information constrained respiratory modeling toward an information-augmentation driven paradigm by incorporating data augmentation, multimodality guidance, prior-informed representation, and improved optimization pipelines.

To propose a multimodal surrogates-guided, multi-task respiratory-modeling framework for simultaneous anatomical motion reconstruction and tumor-tracking.