Publications

Selected Publications [Full list]

Yuhao Qiang*, Mengjia Xu, Mira Patel Pochron, Madhulika Jupelli, Ming Dao. A framework of computer vision-enhanced microfluidic approach for automated assessment of the transient sickling kinetics in sickle red blood cells. Frontiers in Physics, Feb, 2024.
Varghese, A.J., Bora, A., Xu, M.+ and Karniadakis, G.E.. TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers. Neural Networks, Dec, 2023. (Corresponding author) (IF: 7.8)
Xu, M., Galanti, T., Rangamani, A., Rosasco, L. and Poggio, T., The Janus effects of SGD vs GD: high noise and low rank, CBMM Memo 144, 2023.
C Baker, G Smith, EB Marsh, M Funke, JC Mosher, F Maestu, Xu, M.+ D Pantazis, Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline, bioRiv, 2023.10. 23.563643. (Corresponding author)
Galanti, T., Xu, M., Galanti, L., Poggio, T. Norm-based Generalization Bounds for Compositionally Sparse Neural Networks, In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023. (Dec 10-16, New Orleans, LA)
Xu, M., Rangamani, A., Liao, Q., Galanti, T., Poggio, T. Dynamics in Deep Classifiers with Square Loss: Normalization, Low Rank and Neural Collapse. Research, vol.6, January 10, 2023. (IF:11.03) (Highlighted in MIT News)
Shukla, K., Xu, M., Trask, N. and Karniadakis, G. Scalable algorithms for physics-informed neural and graph networks. Data-Centric Engineering, 3, e24-1-e-24-26, 2022.
Xu, M, Singh, V. A. and Karniadakis, G. DynG2G: an efficient stochastic graph embedding method for temporal graphs. IEEE Transactions on Neural Networks and Learning Systems, June 10, 2022. (IF: 14.25)
Xu, M. Understanding graph embedding methods and their applications. SIAM Review, 63(4):825-853, 2021. (Invited paper)
Zhang, Q*, Sampani, K*, Xu, M*, Cai, S, Deng, Y, Li, H, Sun JK, Karniadakis, G. AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images. Translational Vision Science & Technology (TVST), 11 (8), 7-17, 2022. (Co-first author)
Xu, M., Sanz, D., Garces, P., Maestu, F., Li, Q. & Pantazis, D. A graph Gaussian embedding method for predicting Alzheimer’s disease progression with MEG brain networks. IEEE Transactions on Biomedical Engineering, 68(5):1579-1588, 2021. (IF: 4.75)
Xu, M., Wang, Z., Zhang, H., Pantazis, D., Wang, H., & Li, Q. A new Graph Gaussian embedding method for analyzing the effects of cognitive training. PLoS Computational Biology, 16 (9), e1008186, 2020. (IF: 4.78)
Poggio, T., Liao, Q. and Xu, M. Generalization in deep network classifiers trained with the square loss. CBMM Memo 112, 2020.
Qiu, W., Guo, J., Li, X., Xu, M., et al. Multi-label detection and classification of red blood cells in microscopic images,IEEE International Conference on Big Data, 4257-4263, 2020.
Zhang, M.* Li, X.*, Xu, M.*, et al. Automated Semantic Segmentation of Red Blood Cells for Sickle Cell Disease, IEEE Journal of Biomedical and Health Informatics, 2020, 24(11): 3095-3102. (Co-first author) (IF: 7.7)
Zhang, M*., Xu, M.*, Li, Q. RBC Semantic Segmentation for Sickle Cell Disease Based on Deformable U-Net, MICCAI 2018 (Granada, Spain). (Co-first author)
Xu, M., Papageorgiou, D., Abidi, S., Dao, M., Zhao, H. and Karniadakis, G.E. A deep convolutional neural network for classification of red blood cells in sickle cell anemia, PLoS Computational Biology, 13(10): e1005746, 2017. (Top 10% most cited PLOS Computational Biology papers published in 2017, and it has been highlighted in multiple popular media)
Xu, M., Yang, J., Zhao, H., A Multivariate Shape Quantification Approach for Sickle Red Blood Cell Using Patient-Specific Microscopy Image Data. The SPIE 9th International Conference on Digital Image Processing (ICDIP2017), 2017, vol. 10420. (Hong Kong, China).
Xu, M., Yang, J., Zhao, D. and Zhao, H. An image-enhancement method based on variable-order fractional differential operators. Bio-Medical Materials and Engineering, 2015, 26: 1325-1333.
Xu, M., Yang, J., Zhao, H., Zhao, D. Survey of hemodynamics simulation for diagnosis and prediction in vascular disease. Journal of Image and Graphics, 2015, 20(3): 297-310.