Hello! I’m a Software Convergence undergraduate at Kyung Hee University and an undergraduate researcher at the EMIL Lab, advised by Professor Sungha Choi. I study KV cache quantization to cut LLM memory for on-device inference, aiming for work that reaches real products. I also love AI tools and heavily use agentic AI like Grok Bot.
Research Topic: Memory-efficient KV cache quantization for reasoning LLMs (LRMs), in progress.
Built and shipped IGRIS-C’s camera communication system end to end on the physical robot, streaming multiple cameras in real time over LAN and Wi-Fi, now part of its public SDK Camera API.
Studied how ChatGPT is used in elementary-school classrooms through social data analysis.
Founded 찰칵의 덕후, a student-run startup, and built and shipped an iOS app end to end while leading a 5-member team, replacing misleading photo-studio ads with transparent search, comparison, and booking.
Completed mandatory military service.
Streaming long-video understanding with Qwen2-VL-7B: on top of InfiniPot-V KV cache compression, I store the kept KV cache in INT4 instead of FP16, so the model needs fewer KV bytes at the same token budget.
Studying memory-efficient KV cache quantization for reasoning LLMs (in progress).
찰칵의 덕후 — Photo Studio & Photographer Finder App — 사진관과 사진가를 찾아 비교하고 예약·결제까지 하는 모바일 앱 창업 프로젝트 (Mar. 2024 – Jul. 2025). View project →