I am a computer vision research engineer at Apple. I am part of the camera algorithms team developing new camera app features for iPhones and Vision Pro. I am a main contributor to the panorama mode.

Before joining Apple, I obtained my Ph.D degree from Arizona State University where I developed several mathematical models for solving machine learning problems, specifically matching distributional data in the Euclidean space and its applications to clustering, domain adaptation, and point-set registration.

Some Academic Work

Mi, Liang, Azadeh Sheikholeslami, and José Bento. “A family of pairwise multi-marginal optimal transports that define a generalized metric.” Machine Learning 112, no. 1 (2023): 353-384. [arXiv: 2001.11114]

Mi, Liang, “Variational Wasserstein Barycenters for Geometric Clustering”. [arXiv: 2002.10543][code]

Mi, Liang, Wen Zhang, and Yalin Wang. “Regularized Wasserstein Means for Aligning Distributional Data”, Accepted to AAAI 2020. [arXiv: 1812.00338][code]

Zhang, Wen, Liang Mi, Paul M. Thompson, and Yalin Wang. “A Geometric Framework for Feature Mappings in Multimodal Fusion of Brain Image Data.” In International Conference on Information Processing in Medical Imaging, pp. 617-630. Springer, Cham, 2019.

Mi, Liang, Wen Zhang, Xianfeng Gu, and Yalin Wang. “Variational wasserstein clustering.” In Proceedings of the European Conference on Computer Vision (ECCV), pp. 322-337. 2018.
[arXiv] [code]

Mi, Liang, Wen Zhang, Junwei Zhang, Yonghui Fan, Dhruman Goradia, Kewei Chen, Eric M. Reiman, Xianfeng Gu, and Yalin Wang. “An optimal transportation based univariate neuroimaging index.” In Proceedings of the IEEE International Conference on Computer Vision, pp. 182-191. 2017.