Daguang Xu ![](/sites/default/files/person/Daguang.Xu_.jpg) ### Publications ### 2025 [MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss](/publication/2025-08_maisi-v2-accelerated-3d-high-resolution-medical-image-synthesis-rectified-flow) [Can Zhao](/person/can-zhao), Pengfei Guo, [Dong Yang](/person/dong-yang), Yucheng Tang, [Yufan He](/person/yufan-he), Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, [Daguang Xu](/person/daguang-xu) [AAAI 2026](https://arxiv.org/abs/2508.05772) [VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge](/publication/2025-06_vila-m3-enhancing-vision-language-models-medical-expert-knowledge) [Vishwesh Nath](/person/vishwesh-nath), [Wenqi Li](/person/wenqi-li), [Dong Yang](/person/dong-yang), [Andriy Myronenko](/person/andriy-myronenko), Mingxin Zheng, Yao Lu, [Zhijian Liu](/person/zhijian-liu), Hongxu Danny Yin, Yee Man Law, Stephanie Harmon, Benjamin Simon, [Greg Heinrich](/person/greg-heinrich), Stephen Aylward, Marc Edgar, Michael Zephyr, [Pavlo Molchanov](/person/pavlo-molchanov), Baris Turkbey, [Holger Roth](/person/holger-roth), [Daguang Xu](/person/daguang-xu) [CVPR 2025](https://openaccess.thecvf.com/content/CVPR2025/html/Nath_VILA-M3_Enhancing_Vision-Language_Models_with_Medical_Expert_Knowledge_CVPR_2025_paper.html) ### 2024 [FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models](/index.php/publication/2024-07_fedbpt-efficient-federated-black-box-prompt-tuning-large-language-models) Jingwei Sun, [Ziyue Xu](/index.php/person/ziyue-xu), Hongxu Danny Yin, [Dong Yang](/index.php/person/dong-yang), [Daguang Xu](/index.php/person/daguang-xu), Yudong Liu, Zhixu Du, Yiran Chen, [Holger Roth](/index.php/person/holger-roth) [International Conference on Machine Learning 2024](https://proceedings.mlr.press/v235/sun24j.html) [IR-FRestormer: Iterative refinement with fourier-based restormer for accelerated MRI reconstruction](/publication/2024-01_ir-frestormer-iterative-refinement-fourier-based-restormer-accelerated-mri) Mohammad Zalbagi Darestani, [Vishwesh Nath](/person/vishwesh-nath), [Wenqi Li](/person/wenqi-li), [Yufan He](/person/yufan-he), [Holger Roth](/person/holger-roth), [Ziyue Xu](/person/ziyue-xu), [Daguang Xu](/person/daguang-xu), Reinhard Heckel, [Can Zhao](/person/can-zhao) [WACV 2024](https://openaccess.thecvf.com/content/WACV2024/html/Darestani_IR-FRestormer_Iterative_Refinement_With_Fourier-Based_Restormer_for_Accelerated_MRI_Reconstruction_WACV_2024_paper.html) ### 2023 [Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples](/publication/2023-10_communication-efficient-vertical-federated-learning-limited-overlapping-samples) Jingwei Sun, [Ziyue Xu](/person/ziyue-xu), [Dong Yang](/person/dong-yang), [Vishwesh Nath](/person/vishwesh-nath), [Wenqi Li](/person/wenqi-li), [Can Zhao](/person/can-zhao), [Daguang Xu](/person/daguang-xu), Yiran Chen, [Holger Roth](/person/holger-roth) [CVPR 2023](https://openaccess.thecvf.com/content/ICCV2023/html/Sun_Communication-Efficient_Vertical_Federated_Learning_with_Limited_Overlapping_Samples_ICCV_2023_paper.html) [Do Gradient Inversion Attacks Make Federated Learning Unsafe?](/publication/2023-01_do-gradient-inversion-attacks-make-federated-learning-unsafe) [Ali Hatamizadeh](/person/ali-hatamizadeh), Hongxu Danny Yin, [Pavlo Molchanov](/person/pavlo-molchanov), [Andriy Myronenko](/person/andriy-myronenko), [Wenqi Li](/person/wenqi-li), Prerna Dogra, Andrew Feng, Mona G Flores, [Jan Kautz](/person/jan-kautz), [Daguang Xu](/person/daguang-xu), [Holger Roth](/person/holger-roth) [IEEE Transactions of Medical Imaging](https://ieeexplore.ieee.org/abstract/document/10025466) ### 2022 [GradViT: Gradient Inversion of Vision Transformers](/publication/2022-05_gradvit-gradient-inversion-vision-transformers) Ali Hatamizadeh , Hongxu Danny Yin, [Holger Roth](/person/holger-roth), [Wenqi Li](/person/wenqi-li), [Jan Kautz](/person/jan-kautz), [Daguang Xu](/person/daguang-xu), [Pavlo Molchanov](/person/pavlo-molchanov) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022](https://cvpr2022.thecvf.com/) ### 2020 [LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation](/publication/2020-10_lamp-large-deep-nets-automated-model-parallelism-image-segmentation) Wentao Zhu, [Can Zhao](/person/can-zhao), [Wenqi Li](/person/wenqi-li), [Holger Roth](/person/holger-roth), [Ziyue Xu](/person/ziyue-xu), [Daguang Xu](/person/daguang-xu) [MICCAI 2020](https://miccai2020.org/en/) [Weakly Supervised One-stage Vision and Language Disease Detection using Large Scale Pneumonia and Pneumothorax Studies](/index.php/publication/2020-07_weakly-supervised-one-stage-vision-and-language-disease-detection-using-large) Leo Tam, Xiaosong Wang, Evrim Turkbey, Kevin Lu, Yuhong Wen, [Daguang Xu](/index.php/person/daguang-xu) [MICCAI 2020](https://arxiv.org/abs/2007.15778) [When Radiology Report Generation Meets Knowledge Graph](/index.php/publication/2020-04_when-radiology-report-generation-meets-knowledge-graph) Yixiao Zhang, Xiaosong Wang, [Ziyue Xu](/index.php/person/ziyue-xu), Qihang Yu, Alan Yuille, [Daguang Xu](/index.php/person/daguang-xu) [AAAI 2020](https://aaai.org/Conferences/AAAI-20/) [Neurreg: Neural registration and its application to image segmentation](/publication/2020-03_neurreg-neural-registration-and-its-application-image-segmentation) Wentao Zhu, [Andriy Myronenko](/person/andriy-myronenko), [Ziyue Xu](/person/ziyue-xu), [Wenqi Li](/person/wenqi-li), [Holger Roth](/person/holger-roth), Yufang Huang, Fausto Milletari, [Daguang Xu](/person/daguang-xu) [WACV](http://openaccess.thecvf.com/content_WACV_2020/papers/Zhu_NeurReg_Neural_Registration_and_Its_Application_to_Image_Segmentation_WACV_2020_paper.pdf) ### 2019 [4D CNN for semantic segmentation of cardiac volumetric sequences](/publication/2019-10_4d-cnn-semantic-segmentation-cardiac-volumetric-sequences) [Andriy Myronenko](/person/andriy-myronenko), [Dong Yang](/person/dong-yang), Varun Buch, [Daguang Xu](/person/daguang-xu), Alvin Ihsani, Sean Doyle, Mark Michalski, Neil Tenenholtz, [Holger Roth](/person/holger-roth) [MICCAI 2019](https://www.miccai2019.org/) [Privacy-preserving Federated Brain Tumour Segmentation](/publication/2019-10_privacy-preserving-federated-brain-tumour-segmentation) [Wenqi Li](/person/wenqi-li), Fausto Milletari, [Daguang Xu](/person/daguang-xu), Nicola Rieke, Jonny Hancox, Wentao Zhu, Maximilian Baust, Yan Cheng, Sebastien Ourselin, M. Jorge Cardoso, Andrew Feng [MICCAI 2019](https://www.miccai2019.org/) [Cardiac Segmentation of LGE MRI with Noisy Labels](/index.php/publication/2019-10_cardiac-segmentation-lge-mri-noisy-labels) [Holger Roth](/index.php/person/holger-roth), Wentao Zhu, [Dong Yang](/index.php/person/dong-yang), [Ziyue Xu](/index.php/person/ziyue-xu), [Daguang Xu](/index.php/person/daguang-xu) [MICCAI 2019](https://www.miccai2019.org/) [Deep Hierarchical Multi-label Classification of Chest X-ray Images](/index.php/publication/2019-07_deep-hierarchical-multi-label-classification-chest-x-ray-images) Haomin Chen, Shun Miao, [Daguang Xu](/index.php/person/daguang-xu), Gregory D. Hager, Adam P. Harrison [Medical Imaging with Deep Learning](https://2019.midl.io/)