| Jooyong Yi |
| Associate Professor |
| LOFT (Lab of Software) |
| Department of Computer Science and Engineering |
| UNIST |
| Location: Building 106, Room 401-6 |
| E-mail: jooyong at unist.ac.kr |
|
|
|
|
[Research Interests] [News] [Publications] [Services] [Courses] [Current Students] [Alumni] [Research Projects]
I am the head of LOFT (Lab of Software) at UNIST. It is often said that software is everywhere -- it is in your phone, on airplanes, in banks, and within government systems. An alarming trend is the emergence of modern, powerful AI systems that are beginning to take over the task of writing software. This is concerning not just because software developers may lose their jobs; it is also because unless we are careful, we may lose control over the software AI writes.
To prevent this, we are developing autonomous techniques that continuously monitor and address issues within software as they arise. This requires us to develop techniques that can
While the fundamental concepts behind these techniques predate the AI era, the advent of AI has made them even more important. At LOFT, we are at the forefront of advancing these techniques to ensure that AI-written software serves humanity, rather than controlling it.
We have multiple openings for Master's and PhD students. We also welcome undergraduate students who are interested in research. If you are interested, please send me your CV. See here for more details on joining the lab.
January 2025: 
Joint work with Mijung Kim on Lightweight Concolic Testing via Path-Condition Synthesis for Deep Learning Libraries has been accepted to ICSE 2025. With this paper, we have shown that fuzzing efficiency can be significantly improved by exploiting path conditions that are synthesized without using heavyweight symbolic execution. Congratulations to Sehoon Kim!
January 2025: 
I gave a talk on Security Patch Verification in the Shonan Meeting on Trusted Automatic Programming.
October 2024: I gave a talk on Automated Program Repair from Fuzzing Perspective in the Dagstuhl Seminar on Automated Programming and Program Repair.
August 2024: Our paper Enhancing the Efficiency of Automated Program Repair via Greybox Analysis has been accepted to ASE 2024. With this paper, we have shown that by using a greybox approach, APR efficeincy can be significantly improved. Congratulations to YoungJae Kim, Yechan Park, and Seungheon Han!
July 2024: Joint work with Dongsun Kim on Preserving Reactiveness: Understanding and Improving the Debugging Practice of Blocking-call Bugs has been accepted to ISSTA 2024. Congratulations to Arooba Shahoor!
April 2024: 
Our research proposal on Binary Micro-Security Patch Technology Applicable With Limited Reverse Engineering Capability Under SW Supply Chain Environments has been accepted for funding by MSIT.
September 2023: 
Our paper LeakPair: Proactive Repairing of Memory Leaks in Single Page Web Applications received the ACM Distinguished Paper Award at ASE 2023.
September 2023: Our paper Poracle: Testing Patches Under Preservation Conditions to Combat the Overfitting Problem of Program Repair has been accepted and will appear in TOSEM. Congratulations to Elkhan and Mazba!
July 2023: Our demo paper BUGSC++: A Highly Usable Real World Defect Benchmark for C/C++ has been accepted to ASE 2023 Demo. This is joint work with Gabin An, Shin Yoo, Minhyuk Kwon, and Kyunghwa Choi. Our benchmark is available here.
May 2023: Our paper Automated Program Repair from Fuzzing Perspective has been accepted to ISSTA 2023. Congratulations to YoungJae Kim, Seungheon Han, and Khamit Askar.
April 2023: Our research proposal on Large-Language-Model-Based Low-Code Platform Development has been accepted for funding by MSIT.
Feb 2023: Our research proposal on Patch Validation Technique for Automated Program Repair has been accepted for funding by MSIT.
"Those who can imagine anything, can create the impossible." — Alan Turing
[slides] [slides]
ACM Distinguished Paper [slides] [slides]
"Only a life lived for others is a life worthwhile." — Albert Einstein
If you have proficiency in Korean, I highly recommend you watch these videos [v1, v2, v3]. In essence, I suggest you train your neural learning model (a.k.a, your brain) as much as you can in the classroom, using the natural loss function (a.k.a, trial and error).
"A diverse mix of voices leads to better discussions, decisions, and outcomes for everyone." — Sundar Pichai