Welcome to my homepage!
I am an applied research scientist at Amazon Search (A9.com). Before that, I received my PhD degree in Systems Engineering from University of California Berkeley, College of Engineering in May 2018, under supervision of Professor Alexei Pozdnoukhov. Before coming to Berkeley, I obtained my B.S. degree in Urban Informatics and secondary B.A. degree in Economics at Peking University in June 2014.
I am skilled in formulating the machine learning problems and prototyping scalable solutions. I specialize in:
general DL: weak supervisions, self training, data augmentation, model calibration, multi-task & meta learning
problems: extreme multi-label classification, semantic parsing (named entity recognition & entity disambiguation & end-to-end entity linking), deep-learning based ranking
sota pretrained models in computer vision & natural language processing
My Ph.D. training is on understanding complex large-scale systems and developing tools for their design and operation. The understanding of how such systems work requires knowledge about the constitutive laws that govern them, and it also requires an understanding of the theoretical paradigms that are used to model, control and optimize such systems. I have been working on urban cyber-physical systems, societal systems and natural systems.
After academia, I have been working on large scale product search system. When designing NLP features, I also have a systematic view to consider the impact of my features on downstream applications and the whole product search system.