About
Open to Research Collaboration
I work on making AI systems faster and smaller. My research focuses on model compression and hardware-aware optimization — finding the best precision for each layer, and building neural networks that run efficiently on real devices.
Education
Sungkyunkwan University 2023 - 2027
- B.E. in Advanced Semiconductor Engineering 4.2 / 4.5
- B.E. in Systems Management Engineering 4.4 / 4.5
Research
Experience
Undergraduate Researcher
- Precision-scalable neural architectures for compute-efficient inference
- Robust optimization under extreme quantization constraints
AI Software Engineer
- LLM platform with RAG for large-scale enterprise data
- Model quantization and high-performance LLM serving
Software Developer Intern
- Backend development (Java), database architecture
Selected Publications
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Elastic LLMs
Published in arXiv preprint, 2026
* equal contribution, † corresponding author
Recommended citation: https://arxiv.org/pdf/2602.20191
MSQ: Memory-Efficient Bit Sparsification Quantization
Published in ICCV 2025, 2025
* equal contribution, † corresponding author
Recommended citation: https://www.arxiv.org/pdf/2507.22349