Ph.D. Student in Artificial Intelligence at CAU AutoML Lab
Turning research ideas into governed, inspectable AI systems for real-world use
I build language systems that remain useful under noisy, adversarial, and real-world conditions, with as much attention to disciplined execution as model quality.
- I am a Ph.D. student in the Department of Artificial Intelligence at Chung-Ang University, Seoul.
- My work sits at the intersection of trustworthy NLP, autonomous research systems, and LLM-based applications.
- I care about governed workflows, evidence-aware evaluation, and AI systems that can be inspected, resumed, and trusted.
| Topic | Details |
|---|---|
| Current focus | Trustworthy NLP, autonomous research execution, and evidence-aware LLM systems |
| What I build | Research infrastructure, evaluation workflows, and real-world NLP applications |
| Research style | Turning research ideas into governed, inspectable systems instead of one-off demos |
| Core themes | Robust language understanding, deployment discipline, and experiment governance |
| Based in | Seoul, Korea |
An operating system for autonomous research. AutoLabOS structures literature review, hypothesis generation, experiment planning, review gating, and manuscript drafting as a checkpointed and inspectable workflow rather than a single generation step.
- Fixed multi-stage workflow for research execution instead of open-ended agent drift
- Checkpointed runs with inspectable artifacts and resumable progress
- Evidence-bound claim review that limits conclusions to what a run actually supports
- Terminal and web interfaces for operating autonomous research pipelines
Built with: TypeScriptNode.jsReactOpenAICodex CLISemantic Scholar
- H. Lee, C. Lee, Y. Lee, J. Lee. "BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks," Findings of NAACL 2025, New Mexico, USA, April 29 - May 4, 2025. Paper
- K. Kim, H. Lee, J. Lee. "GoodGPT: Counseling-chat," ICCE 2025, Las Vegas, USA, January 11 - 14, 2025.
- C. Lee, H. Lee, K. Kim, S. Kim, J. Lee. "An Efficient Fine-Tuning of Generative Language Model for Aspect-Based Sentiment Analysis," ICCE 2024, Las Vegas, USA, January 5 - 8, 2024.
- H. Lee, J. Lee. "Exploitation of Character-Wise Language Model for Recovering Adversarial Text," ICEIC 2023, 2023.
- A. Moon, S. Lee, S. Cho, T. Lee, H. Lee, J. Lee. "An Efficient Neural Network based on Early Compression of Sparse CT Slice Images," PlatCon 2021, pp. 1-5. doi:
10.1109/PlatCon53246.2021.9680749
| Period | Journey |
|---|---|
2024.03 - Present | Ph.D. Course, Department of Artificial Intelligence, Chung-Ang University |
2022.03 - 2024.02 | M.Sc. Course, Department of Artificial Intelligence, Chung-Ang University |
2021.09 - 2021.12 | Intern, S2W Inc. |
2015.03 - 2022.02 | B.Sc. Course, School of Computer Science and Engineering, Chung-Ang University |
2013.03 - 2015.02 | Hansung Science High School |
Awards
- 3rd Prize, 2022 AI Graduate School Challenge, LG
- 3rd Prize, 2021 Text Ethics Verification Data Hackathon Competition, National Information Society Agency (NIA)
Selected Builds and R&D
2025 - PresentAutoLabOS: autonomous research system for literature-grounded, checkpointed, and inspectable workflows2023.09 - 2024.12Automatic Generation of Children's Song Lyrics and Improvement of Lyric Quality Based on Large Language Model2023.03 - 2024.12Integrated Framework for Automatic Neural Network Generation and Deployment Optimized for Runtime Environments In cooperation with ETRI (Electronics and Telecommunications Research Institute)
Languages
AI / ML
Web / App / Tools
This card is generated automatically by GitHub Actions.
