I am currently a research scientist at Google Brain. I am working on deep learning and its applications in text-to-speech and speech recognition.

I completed my PhD at MIT working with Prof. Vivienne Sze on energy efficient autonomous navigation algorithms and systems.

I complete my master thesis under the supervision of Prof. Edward H. Adelson on computational photography.

Before I joined MIT, I worked at Microsoft Research Asia with Prof. Yi Ma on 3D reconstruction and rank minimization.

I finished my undergraduate study at Tsinghua Xuetang Special Pilot CS Class (Yao Class) supervised by Turing Award Winner Prof. Andrew Chi-Chih Yao in Institute of Interdisciplinary Information Sciences, Tsinghua University.

My research interest spans the area of sparsity, low-rank matrix recovery, symmetry/regularity of textures, 3D computer vision, computational photography, object detection, video compression, localization, mapping.