Xinyu Wang

Xinyu Wang

Assistant Professor
Computer Science and Engineering
University of Michigan, Ann Arbor
Email: xwangsd@umich.edu
Office: 4620 Beyster

[Research] [Teaching] [Publications] [Students] [Service] [CV]

What's new?!

(!!) Multiple PhD positions available. Application deadline is December 15, 2021. Apply here!

(!!) A couple of NSF REU positions available. Please email me with your resume and transcripts if you're interested!

Prospectives students: take a look at this link.

I am an assistant professor in the Electrical Engineering and Computer Science Department at the University of Michigan.
My research interests are generally in the areas of programming languages, formal methods, software engineering, and artificial intelligence. I am particularly interested in developing intelligent programming systems that allow programmers and non-programmers to create reliable software easily in a correct-by-construction manner.
Previously I was a researcher at Microsoft. I obtained my Ph.D. from the University of Texas at Austin.

Research

My current research is primarily centered around the topic of program synthesis. This is an emerging field at the intersection of programming systems and artificial intelligence. The basic idea is to make the software development process much easier and more realiable by raising the level of abstraction at which the software behavior is specified. For instance, I have developed several programming-by-example systems that enable end-users to create programs by specifying the desired program's behavior using a few examples. Beyond developing practical systems, I am also excited about understanding the fundamentals of program synthesis. My long-term research goal is to build fundamental intelligent programming techniques that are also useful in practice. Towards this goal, I am currently exploring the following problems.

What are important domains that can benefit from program synthesis and how to build practical systems for these domains?

How to make program synthesis more usable, in particular, by enriching the interaction modalities with human users?

How to design fundamental synthesis algorithms that are general, efficient, generalizable, and multi-modal?

Teaching

EECS 481. Software Engineering [Winter 2022]

EECS 598. Intelligent Programming Systems [Fall 2021]

EECS 498. Intelligent Programming Systems [Fall 2021]

EECS 203. Discrete Mathematics [Winter 2021]

EECS 598. Program Synthesis: Techniques and Applications [Fall 2020]

Publications

Web Question Answering with Neurosymbolic Program Synthesis [pdf] [code] Jocelyn Chen, Aaron Lamoreaux, Xinyu Wang, Greg Durrett, Osbert Bastani, Isil Dillig Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 2021
Synthesizing Data Structure Refinements from Integrity Constraints [pdf] Shankara Pailoor, Yuepeng Wang, Xinyu Wang, Isil Dillig Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 2021
Interpretable Program Synthesis [pdf][code] Tianyi Zhang, Zhiyang Chen, Yuanli Zhu, Priyan Vaithilingam, Xinyu Wang, Elena Glassman Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI), 2021
Automated Policy Synthesis for System Call Sandboxing [pdf] ACM SIGPLAN Distinguished Paper Award Shankara Pailoor, Xinyu Wang, Hovav Shacham, Isil Dillig Proceedings of the ACM on Programming Languages (OOPSLA), 2020
Sketch-Driven Regular Expression Generation from Natural Language and Examples [pdf][code] Xi Ye, Qiaochu Chen, Xinyu Wang, Isil Dillig, Greg Durrett Transactions of the Association for Computational Linguistics (TACL), 2020
Interactive Program Synthesis by Augmented Examples [pdf][code] Tianyi Zhang, London Lowmanstone, Xinyu Wang, Elena Glassman Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), 2020
Multi-Modal Synthesis of Regular Expressions [pdf][code] Qiaochu Chen, Xinyu Wang, Xi Ye, Greg Durrett, Isil Dillig Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 2020
An Efficient Programming-by-Example Framework [pdf] Xinyu Wang Ph.D. dissertation, 2019
Relational Program Synthesis [pdf] Yuepeng Wang, Xinyu Wang, Isil Dillig Proceedings of the ACM on Programming Languages (OOPSLA), 2018
Learning Abstractions for Program Synthesis [pdf] Xinyu Wang, Greg Anderson, Isil Dillig, Ken McMillan International Conference on Computer Aided Verification (CAV), 2018
Automated Migration of Hierarchical Data to Relational Tables using Programming-by-Example [pdf][code] Navid Yaghmazadeh, Xinyu Wang, Isil Dillig Proceedings of the VLDB Endowment (VLDB), 2018
Program Synthesis using Abstraction Refinement [pdf] Xinyu Wang, Isil Dillig, Rishabh Singh Proceedings of the ACM on Programming Languages (POPL), 2018
Synthesis of Data Completion Scripts using Finite Tree Automata [pdf] Xinyu Wang, Isil Dillig, Rishabh Singh Proceedings of the ACM on Programming Languages (OOPSLA), 2017
FIDEX: Filtering Spreadsheet Data using Examples [pdf] Xinyu Wang, Sumit Gulwani, Rishabh Singh Proceedings of the ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA), 2016
EXPLORER : Query- and Demand-Driven Exploration of Interprocedural Control Flow Properties [pdf] Yu Feng, Xinyu Wang, Isil Dillig, Calvin Lin Proceedings of the ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA), 2015
Bottom-up Context-Sensitive Pointer Analysis for Java [pdf] Yu Feng, Xinyu Wang, Isil Dillig, Thomas Dillig Asian Symposium on Programming Languages and Systems (APLAS), 2015

Students

Rui Dong (PhD student, 2021-)

Service

2022: PLDI (AEC co-chair and PC), OOPSLA (PC), SYNT (PC)

2021: PLDI (PC), APLAS (PC), SPLASH SRC (Reviewer and Judge)

2020: CAV (AEC co-chair and PC), SYNT (PC)

2019: SAS (AEC PC)