About

My name is Zexuan Zhong. I am a first-year thesis-track M.S. student at Department of Computer Science, University of Illinois at Urbana-Champaign. I am now working with Prof. Tao Xie on applying machine learning to address software engineering problems. Before that, I received a B.S. in Computer Science from Peking University, where I worked with Prof. Yingfei Xiong on program analysis and automatic bug fixing. I was also a full-time research intern at Microsoft Research Asia.
Besides software engineering and machine learning research, I am very interested in intersection between computer vision and computer graphics with topics such as computational photography, digital image editing, image-based rendering, and 3D modeling. I have done several projects on these fields.

Publications

  1. CoLink: An Unsupervised Framework for User Identity Linkage
    Zexuan Zhong, Yong Cao, Mu Guo, Zaiqing Nie
    AAAI 2018
  2. Generating Regular Expressions from Natural Language Specifications: Are We There Yet?
    Zexuan Zhong, Jiaqi Guo, Wei Yang, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang
    AAAI 2018 workshop on NLP for Software Engineering

Selected Projects

Regexs generation from NL sentences (ongoing)
We focus on automatically generating regular expressions from natural language specifications. Current state-of-the-art approach reduces the target problem to a general machine translation task. We conduct an empirical study which shows a huge drop of performance when applying current state-of-the-art on real-world data vs synthetic data. We propose to utilize testability of regular expression to make improvement.
User Identity Linkage
User Identity Linkage refers to match identical users across two social networks. In this project, we propose an unsupervised framework based on co-training to address this problem. We develop an attribute-based model and a relationship-based model. The models will be enhanced in iterative way via co-training. We also propose to employ sequence-to-sequence learning to measure the similarity of attributes.
DualFocus
DualFocus is a tool for image refocusing. DualFocus takes two images with different local lengths as input, and outputs an all-in-focus image. Based on characteristics of natural in-focus images, we design a object function with two variables to optimize, and employ Alternating Direction Method of Multipliers (ADMM) to solve a deconvolution problem. DualFocus does not require modification of cameras (i.e., coded aperture), and outperformances single-image-based refocusing approaches.
ObjRender
ObjRender is a tool to render 3D synthetic objects in images. We use a mirror ball as a light probe and take several low dynamic range (LDR) images of the mirror ball to recover a high dynamic range (HDR) image. We build the environment lighting box by mapping the HDR image in sphere domain to the equirectangular domain. We annotate necessary geometry models such as tables in the scene, and render the synthetic objects on those models.
Image Inpainting
Given an image with a hole, we synthesize texture from neighbor regions and fill the texture into the hold. To find the visually plausible texture to be used to fill, we select the sample with similar overlapping region. To preserve edges of objects in the image, we define a priority function based on gradient magnitude.
Water Simulation
In this project, we simulate the surface of the water in a pool. To simulate the ripple on the water, we use normal map during illumination calculation, i.e., we change the normal of each point of the models, instead of changing the water models.

Education

  • 2017.8 - present, University of Illinois at Urbana-Champaign
    M.S. in Computer Science
  • 2013.9 - 2017.7, Peking University
    B.S. in Computer Science and Technology

Experience

  • 2017.8 - present, Research Assistant, University of Illinois at Urbana-Champaign
    Advisor: Prof. Tao Xie
  • 2016.7 - 2017.5, Research Intern, Microsoft Research Asia
    Mentors: Dr. Zaiqing Nie and Dr. Yong Cao
  • 2015.11 - 2016.5, Research Assistant, Peking University
    Advisor: Prof. Yingfei Xiong

Honors

  • Tang Li-Xin Scholar (4 in 400), 2014 - present
  • Peking University Outstanding Graduate, 2017
  • Bachelor of Science Summa Cum Laude, 2017
  • Peking University Merit Student, 2014 - 2017

Program Contests

  • Gold Medal, ACM-ICPC Mid-Central USA Regionals Chicago site, 2017
  • Gold Medal, ACM-ICPC Asia Regionals Changchun site, 2013
  • First Prize, China National Olympiad in Informatics, 2012

Contact

3107 Siebel Center
201 N. Goodwin Ave.
Urbana, IL 61801, USA
Email: zexuan2@illinois.edu