Research Portfolio
Jiwon Song | 송지원
Ph.D. Student @ SNU VLSI Lab
Electrical and Computer Engineering, Seoul National University
Building efficient AI systems for long-context and reasoning-heavy LLM inference.
Research interests in Efficient AI systems — model-level optimization (quantization, pruning), hardware-aware optimization, and serving system optimization, with a focus on LLM inference.
News
Recent updates on publications, milestones, and research-related announcements.
FastKV is accepted to ACL 2026 Findings.
Publications
Research on efficient inference, reasoning acceleration, and practical system optimization for large language models.
LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning
arXiv preprint arXiv:2510.14211
Education
Ph.D. Student (Integrated M.S./Ph.D. Program)
Electrical and Computer Engineering, Seoul National University
Advisor: Jae-Joon Kim
Bachelor of Science
Electrical and Computer Engineering, Seoul National University
Summa Cum Laude 3.9/4.3
Experiences
Technical Writer
SqueezeBits
- Tech blog writing comparing vLLM and TensorRT-LLM
vLLM vs TensorRT-LLM #6: Weight-Only Quantization
vLLM vs TensorRT-LLM #8: KV Cache Quantization
Teaching Assistant
Dept. of Electrical and Computer Engineering, Seoul National University
- 430.207B 기초전자회로 및 실험 (Introduction to Electronic Circuits)
Undergraduate Researcher
VLSI Lab, Seoul National University
- LLM Quantization and Pruning
Undergraduate Researcher
SqueezeBits
- DNN Quantization
Undergraduate Researcher
VLSI Lab, Seoul National University
- Post-training Quantization of vision transformers
Military Service
Republic of Korea Army
- Sergeant