Joy Jingyi Xu 续婧怡

About Me

I’m an Advanced Software Engineer at Siemens NX CAD (Computer-Aided Design), and I’ve been on the NX Diagramming team since 2022.

Previously, I was a doctoral student at Northeastern University’s Network Science Institute, advised by Prof. Tina Eliassi-Rad. My research focused on graph embedding methods at the intersection of mathematics, computer science, and network science. I’m especially interested in combining machine learning with classic algorithms and in building practical models for estimation and prediction. My broader interests include network science, machine learning, data mining, and algorithms. I left my PhD program in 2021 to focus on building software, learning beyond formal boundaries, and pursuing fast feedback loops through real-world products.

I earned my master’s degree in Computer Science from the University of California, Los Angeles (UCLA), in 2018, with a focus on machine learning. I co-authored research with my lab and Prof. Guy Van den Broeck, published at ICML 2018.

I earned my bachelor's degree in Mathematics, with a minor in Computer Science, from the University of Michigan in 2014. Before returning to graduate school in UCLA Computer Science in 2016, I worked as an actuary in the Asset Liability Management Department at Sun Life Financial in the Boston metropolitan area.

Technical Skills & Interests

Programming Languages & Software Development: I am experienced with C++ through professional software development, including building and maintaining production-level systems. I am proficient in Python, especially for research, scripting, automation, and rapid experimentation. I write requirement specs, functional specs, design docs, and coding plans for production-level projects.
AI-Assisted Development: I write Skills, Reference docs, and Sub-Agents, to assist with code generation and debugging.
Communication, Mentorship & Knowledge Transfer: I am known for clear and effective communication, mentorship, and the ability to explain complex ideas in a simple way. I intentionally verify understanding, establish alignment and close communication loops. I actively share knowledge through documentation, code reviews, and presentations. I have experience mentoring interns, helping them grow their skills and navigate their careers.

Self-Initiated Projects

Peter Lynch Stock Analysis Tool: I built a Python web app that analyzes stocks using Peter Lynch’s investment methodology. Enter any stock ticker to get an instant Lynch-style analysis — PEG ratio, 10-bagger potential, a dividend-adjusted Lynch formula, debt assessment, and an overall Lynch Score with a Buy/Hold/Avoid recommendation. I also built a browser-based UI to explore the results visually. Investment App
Software Construction Project: Together with the team, we built a tool that converts research PDFs into audio so users can listen to papers more easily. Existing text-to-speech tools often read table contents, headers, and footnotes aloud, which can make papers hard to follow. Our tool identifies and removes URLs, headers, footnotes, and math formulas, improving comprehension. Future work includes making text-to-speech systems render math formulas more naturally. Software Construction Project Joint work with Hanjun Li, Sherry Lin, Andres Abdo, Yunsheng Bai.

Research and Publications

Machine Learning Research: Developing constraint-aware objectives for neural networks. Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang and Guy Van den Broeck. A Semantic Loss Function for Deep Learning with Symbolic Knowledge, In Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. 📄 758 citations by 2026
Graph Embedding Research: To better understand the mathematics behind why neural networks work so well, I compared six network-embedding methods across three categories: matrix factorization, random-walk approaches, and deep architectures. We demonstrated that matrix factorization methods correlate with deep neural-network embedding methods. Understanding Graph Embedding Methods and Their Applications
Algorithm Research: Finding an optimal solution for the mutually exclusive set cover problem. (Individual project) Project repository
Robotics Research: Evacuation planning using HoloLens and RTAB-Map SLAM. (Joint project with Hangxin Liu, Zhenliang Zhang, and Yixin Zhu) Project repository

Course Name	Organization	Year
Robotics: Computational Motion Planning	Coursera	2018
Machine Learning	Coursera Andrew Ng	2017
Algorithms	University of Hawaii	2016
Linear Algebra	MIT OCW	2018

Joy Jingyi Xu 续婧怡

About Me

Technical Skills & Interests

Self-Initiated Projects

Research and Publications

Online Classes Taken Outside School