Jie “JW” Wu | UBC, GW, SJTU, Ex-Snap Inc., Ex-MSR, Ex-Google Research

About JW

My original first name is 杰 (Jie). I also go by JW. How to pronounce Jie? Please see this link with audio to learn how to pronounce Jie (“JEE-yeh” is pretty close). I’m happy to accept any approximation, so please feel free to use your favorite variants!

I’m a postdoc at University of British Columbia, working with Dr. Fatemeh Fard at the intersection of GenAI and Software Engineering. My undergraduate and master studies were done both in Computer Science at Shanghai Jiao Tong University (at ACM Class, an elite CS program at SJTU). I received my PhD in Systems Engineering at George Washington University. My PhD dissertation is titled “Towards Formalizing Data-Driven Decision-Making from Big Data: A Systematic Multi-Criteria Decision-Making Approach in Online Controlled Experiments”. I was a research intern at Google Research and Microsoft Research Asia. I publish under “Jie JW Wu”.

I worked as a software engineer in the industry for nearly a decade at Snap Inc. (Seattle office), Microsoft (Redmond HQ), and startup (ArcSite, Shanghai office). I’ve worked in various areas such as ML-enabled recommender systems, data analysis, scalable backend service and infrastructure, mobile applications, etc.

Research

The goal of my research is to build Trustworthy AIware. Industries are transitioning from software to AIware, i.e., AI-powered software, which will greatly democratize software creation and ease the jobs of 27 million professional software engineers in the world. Therefore, How to build reliable and safe software is critical for society, especially in the current era of Large Language Models (LLMs).

I’m interested in developing a systems thinking approach that emphasizes connections, feedback loops, layers, and new processes to address the trustworthiness issues in AIware. In the future, I plan to use this approach to enhance more dimensions of trustworthiness such as controllability, safety, and robustness for AIware components. I believe systems thinking will provide a new perspective that complements the statistical and reductionist view, a new language for communicating AIware components and relationships, and new tools that form fundamental, practical building blocks in the evolution of trustworthy AIware.

Keywords: AI for Software Engineering (AI4SE), Software Engineering for AI (SE4AI), Large Language Models (LLMs), Data Science, Systems Science and Engineering

Teaching

I’m an instructor teaching COSC 320 “Analysis of Algorithm” for undergrads at UBC Okanagan for this term. We adopted a new learner-centered approach in this course. It’s been fun and I enjoyed talking to students!

News

⚡ Oct 2024: I’m honored to be a Program Committee Member of RAIE 2025. Looking forward to the submissions and reviews!

⚡ Oct 2024: I’m a reviewer for Journal of Software and Systems.

⚡ Sep 2024: I’m an instructor teaching COSC 320 “Analysis of Algorithm” for undergrads at UBC Okanagan for this term. We adopted a new learner-centered approach in this course. It’s been fun and I enjoyed talking to students!

⚡ Sep 2024: I’m honored to be a Program Committee Member of SANER 2025 Tool and Demo Track. Looking forward to the submissions and reviews!

⚡ Aug 2024: I’m honored to be a Program Committee Member of CAIN 2025. Looking forward to the submissions and reviews!

⚡ Jun 2024: I’m glad to attend SEMLA 2024 to present my poster for our work in benchmarking the communication skills of Code LLM and LLM Agent! I’m grateful for the travel support and travel grant award from SEMLA.

⚡ May 2024: My paper on automating offline A/B testing (AutoOffAB) is accepted at FSE 2024, “Ideas, Visions and Reflections” Track!

⚡ May 2024: I’m excited to share that my paper on the use of V-Model in ML-enabled system will appear in the IEEE Software Practitioner’s digest column!

⚡ Mar 2024: I’m honored to be invited as a Program Committee Member of ASE 2024 Artifact Evaluation Track. Looking forward to the submissions and reviews!

⚡ Feb 2024: I’m honored to share that my paper on the use of V-Model in ML-enabled system has been selected as a candidate for the CAIN 2024 Best Paper Award!

⚡ Feb 2024: I’m honored to be invited as a Program Committee Member of FSE 2024 Posters Track. Looking forward to the submissions and reviews!

⚡ Feb 2024: My paper on investigating the use of V-Model in ML-enabled system is accepted at CAIN 2024 (3rd International Conference on AI Engineering – Software Engineering for AI)! Looking forward to the event in Lisbon, Portugal. I gratefully thank SIGSOFT CAPS for the travel support award.

⚡ Jan 2024: Our paper on investigating LLM in Code Clone Detection is accepted at ICPC 2024 (International Conference on Program Comprehension 2024). Congrats to Mohamad!

⚡ Nov 2023: I will attend MAPS 2023 on Dec 3, 2023, in San Francisco, US to present my work on the communication skills of LLM. Looking forward to the event! I gratefully thank NSF for the travel support award.

⚡ Nov 2023: I will be a Postdoctoral Research Fellow at University of British Columbia, Canada, working with Dr. Fard at the intersection of Software Engineering and AI!

Publications

LLM Survey on Low Resource PL

A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages

Sathvik Joel, Jie JW Wu, Fatemeh Hendijani Fard

@article{joel2024survey, title={A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages}, author={Joel, Sathvik and Wu, Jie JW and Fard, Fatemeh H}, journal={arXiv preprint arXiv:2410.03981}, year={2024} }

(long paper, under review)
MergeRepair

MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair

Meghdad Dehghan, Jie JW Wu, Fatemeh Hendijani Fard, Ali Ouni

@article{dehghan2024mergerepair, title={MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair}, author={Dehghan, Meghdad and Wu, Jie JW and Fard, Fatemeh H and Ouni, Ali}, journal={arXiv preprint arXiv:2408.09568}, year={2024} }

(Accepted RR. To submit to EMSE)
LLM Communication Benchmark

Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent

Wu, Jie JW, Fatemeh Hendijani Fard

Code Poster @article{wu2024benchmarking, title={Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent}, author={Wu, Jie JW and Fard, Fatemeh H}, journal={arXiv preprint arXiv:2406.00215}, year={2024} }

(long paper, under review)
Autmoated Offline AB

AutoOffAB: Toward Automated Offline A/B Testing for Data-Driven Requirement Engineering

Wu, Jie JW

32nd ACM International Conference on the Foundations of Software Engineering (FSE ’24, Ideas, Visions and Reflections Track)

Arxiv @inproceedings{wu2024autooffab, title={AutoOffAB: Toward Automated Offline A/B Testing for Data-Driven Requirement Engineering}, author={Wu, Jie JW}, booktitle={Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering}, pages={472--476}, year={2024} }
Code Clone Detection

Investigating the Efficacy of Large Language Models for Code Clone Detection

Khajezade, Mohamad, Jie JW Wu, Fatemeh Hendijani Fard, Gema Rodríguez-Pérez,Mohamed Sami Shehata

International Conference on Program Comprehension (ICPC 2024), Early Research Achievements (ERA) (short paper)

Arxiv @inproceedings{khajezade2024investigating, title={Investigating the Efficacy of Large Language Models for Code Clone Detection}, author={Khajezade, Mohamad and Wu, Jie JW and Fard, Fatemeh Hendijani and Rodr{\'\i}guez-P{\'e}rez, Gema and Shehata, Mohamed Sami}, booktitle={Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension}, pages={161--165}, year={2024} }
V-Model

An Exploratory Study of V-Model in Building ML-Enabled Software: A Systems Engineering Perspective

Wu, Jie JW

3rd International Conference on AI Engineering – Software Engineering for AI (CAIN 2024) (long paper) Distinguished Paper Award Candidate. Selected to appear in IEEE Software Practioners' Digest column.

Slides @inproceedings{wu2024exploratory, title={An Exploratory Study of V-Model in Building ML-Enabled Software: A Systems Engineering Perspective}, author={Wu, Jie JW}, booktitle={3rd International Conference on AI Engineering – Software Engineering for AI (CAIN 2024)}, note={Lisbon, Portugal} }
LLM Communication

Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code

Wu, Jie JW

The 7th Annual Symposium on Machine Programming (MAPS ’23 Workshop)

Slides @inproceedings{wu2023large, title={Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code}, author={Wu, Jie JW}, booktitle={The 7th Annual Symposium on Machine Programming (MAPS ’23 Workshop)}, note={Workshop, December 3, 2023, San Francisco, CA, USA} }
Dissertation

Towards Formalizing Data-Driven Decision-Making from Big Data: A Systematic Multi-Criteria Decision-Making Approach in Online Controlled Experiments

Wu, Jie JW

Ph.D. Dissertation

Slides @phdthesis{wu2023towards, title={Towards Formalizing Data-Driven Decision-Making from Big Data: A Systematic Multi-Criteria Decision-Making Approach in Online Controlled Experiments}, author={Wu, Jie JW}, year={2023}, school={The George Washington University} }
MOVSW

A Multi-Objective Evolutionary Approach Towards Automated Online Controlled Experiments

Wu, Jie JW, Thomas A. Mazzuchi, and Shahram Sarkani

Journal of Systems and Software, 2023.

Pre-print Code @article{wu2023multi, title={A multi-objective evolutionary approach towards automated online controlled experiments}, author={Wu, Jie JW and Mazzuchi, Thomas A and Sarkani, Shahram}, journal={Journal of Systems and Software}, pages={111703}, year={2023}, publisher={Elsevier} }
LDM

Comparison of Multi-Criteria Decision-Making Methods for Online Controlled Experiments in a Launch Decision-Making Framework

Wu, Jie JW, Thomas A. Mazzuchi, and Shahram Sarkani

Information and Software Technology 155 (2023): 107115.

Pre-print Code Slides @article{wu2023comparison, title={Comparison of multi-criteria decision-making methods for online controlled experiments in a launch decision-making framework}, author={Wu, Jie JW and Mazzuchi, Thomas A and Sarkani, Shahram}, journal={Information and Software Technology}, volume={155}, pages={107115}, year={2023}, publisher={Elsevier} }
Offline Sketch Parsing

Offline Sketch Parsing via Shapeness Estimation

Wu, Jie, Changhu Wang, Liqing Zhang, Yong Rui

IJCAI. Vol. 15. 2015. (long paper, acceptance rate:28.6%) (M.S. Thesis)
Online Sketch Recognition

Sketch Recognition with Natural Correction and Editing

Wu, Jie, Changhu Wang, Liqing Zhang, Yong Rui

Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 28. No. 1. 2014. (long paper, acceptance rate:28.0%) (M.S. Thesis)

Video
SmartVisio

Smartvisio: Interactive sketch recognition with natural correction and editing

Wu, Jie, Changhu Wang, Liqing Zhang, Yong Rui

Proceedings of the 22nd ACM international conference on Multimedia. 2014. (demo paper) (M.S. Thesis)

Video
Gestalt Saliency

Gestalt saliency: Salient region detection based on gestalt principles

Wu, Jie, Liqing Zhang

2013 IEEE International Conference on Image Processing. IEEE, 2013. (B.S. Thesis)
Search Ranking

Numeric query ranking approach

Wu, Jie, Yi Liu, Ji-Rong Wen

Proceedings of the 22nd International Conference on World Wide Web. 2013. (poster paper)

Misc

Outside research and software engineering, I’m interested in the following topics, and I’m happy to talk about it if you find any of them interesting:

红楼梦 (Dream of the Red Chamber): Arguably the best 18th-century Chinese novel that describes the rise and fall of 贾’s family. I’m speechless about how great the realism is in the stories. Furthermore, on top of these highly realistic stories, a higher layer exists that implies Confucianism, Buddhism, and Taoism from Chinese philosophy!
Albert Einstein and history of Relativity, Quantum Physics: If Einstein’s deeds were written into a novel, I would not believe that it would happen in the real world!
Basketball: I (used to) play every week
Reading: with a general focus on History, Non-fiction, and Philosophy