Hyunjae Suh

University of California, Irvine

Irvine, CA, USA

hyunjas@uci.edu

I am a third-year Software Engineering Ph.D. candidate at the University of California, Irvine, where I work under the guidance of Professor Iftekhar Ahmed in the STAIRS lab. Prior to joining UC Irvine, I completed my bachelor’s degree in computer science at Kookmin University.

My work centers on AI for software engineering, using large language models and LLM agents to support and evaluate software development. I am interested in the attribution and provenance of AI-generated code, the empirical evaluation of LLMs for software engineering tasks, and reliable AI-assisted development. My research has appeared at ICSE, ASE, and ACM TOSEM, and has driven real-world impact through applied science internships at Amazon.

Feel free to reach out if you’d like to chat about research or collaboration. You can find my publications and my CV on this site.

News

May 01, 2026	Our industry paper “Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video” was accepted to the ASE 2026 Industry Showcase, based on my internship work at Amazon.
Jan 15, 2026	Our paper “An Empirical Study on Evaluating Accessible Code Generation Capabilities of LLMs” was accepted to ACM TOSEM.
Apr 01, 2025	Presented “An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?” at ICSE 2025.

Selected Publications

ASE
Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video

Mayur Kurup*, Hyunjae Suh*, Swathi Vaidyanathan, Pranesh Vyas, Srinidhi Madabhushi, and Yegor Silyutin

In IEEE/ACM International Conference on Automated Software Engineering (ASE), Industry Showcase . *Equal contribution (co-first authors) , 2026

Abs arXiv Bib

An industry case study, conducted at Amazon Prime Video, on assessing the risk of software deployments using diff-aware features derived from code changes. We show how features extracted from code diffs can be used to predict the likelihood that a given deployment introduces a regression, helping teams prioritize review and testing effort.
@inproceedings{kurup2026deployment, title = {Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video}, author = {Kurup*, Mayur and Suh*, Hyunjae and Vaidyanathan, Swathi and Vyas, Pranesh and Madabhushi, Srinidhi and Silyutin, Yegor}, year = {2026}, booktitle = {IEEE/ACM International Conference on Automated Software Engineering (ASE), Industry Showcase}, }
TOSEM
An Empirical Study on Evaluating Accessible Code Generation Capabilities of LLMs

Hyunjae Suh, Mahan Tafreshipour, Sam Malek, and Iftekhar Ahmed

ACM Transactions on Software Engineering and Methodology (TOSEM), 2026

Abs Bib HTML

We study how well Large Language Models generate web-accessible code compared to human developers. Comparing code generated by GPT-4o and Qwen2.5-Coder against human-written code, we find that LLMs frequently produce more accessible code for basic features but struggle with complex issues such as ARIA attributes. We evaluate advanced prompting strategies (Zero-Shot, Few-Shot, Self-Criticism) and introduce FeedA11y, a feedback-driven ReAct-based approach that outperforms the other methods, underscoring the need for feedback-based techniques to improve accessibility.
@article{hyunjae2026accessible, title = {An Empirical Study on Evaluating Accessible Code Generation Capabilities of LLMs}, author = {Suh, Hyunjae and Tafreshipour, Mahan and Malek, Sam and Ahmed, Iftekhar}, year = {2026}, journal = {ACM Transactions on Software Engineering and Methodology (TOSEM)}, doi = {10.1145/3820782}, }
ICSE
An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?

Hyunjae Suh, Mahan Tafreshipour, Jiawei Li, Adithya Bhattiprolu, and Iftekhar Ahmed

In IEEE/ACM International Conference on Software Engineering (ICSE) , 2025

Abs arXiv Bib HTML

As LLMs become popular for code generation, detecting whether source code was written by a human or an AI is increasingly important for quality and licensing reasons. We empirically evaluate existing AI-generated code detectors and find that they all perform poorly and lack generalizability. We propose improved approaches based on fine-tuning LLMs and machine-learning classifiers using static code metrics and AST-derived embeddings. Our best model outperforms the state-of-the-art detector GPTSniffer, achieving an F1 score of 82.55, and we conduct an ablation study on the contribution of different code features.
@inproceedings{hyunjae2025aidetector, title = {An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?}, author = {Suh, Hyunjae and Tafreshipour, Mahan and Li, Jiawei and Bhattiprolu, Adithya and Ahmed, Iftekhar}, year = {2025}, booktitle = {IEEE/ACM International Conference on Software Engineering (ICSE)}, }