cv

Research Intern

Omnimodal Foundation Model Office, SK Telecom

Providing Benchmarks and Post-training Techniques for Large Language Models capable of Understanding Korean

Server Manager

Thunder Research Group

Built and managed a 1.2 PB Lustre distributed file system and a GPU cluster with 63 nodes (278 GPUs) serving 300+ users.

Researcher

Thunder Research Group, Seoul National University

Improving model quality with corpus engineering

• Most Used Languages: C++, Python
• Advisor: Prof. Jaejin Lee

Teaching Assistant

CSE courses (Seoul National University)

• Algorithms (2022.09-2022.12)
• System Programming (2025.03-2025.06)

Summer Intern (DevOps team)

TmaxTibero

Composing Network of DBMS containers and Parallelizing test tasks for Test Automation

• Most Used Technology: Python Parallel Programming, Shell, Docker, Docker Compose

Undergraduate Researcher (UROP)

CSAP Lab, Seoul National University

Implemented DNN operation with cuda programming apis & Evaluated DNN Post-training Quantization results

• Most Used Languages: C++, Python
• Advisor: Prof. Bernhard Egger

Tutor

Foundation of Computing Course (Seoul National University)

• Teaching language: Python
• Practice session teaching assistant

Member Relations & Systems Administrator

Bacchus (SNU CSE Computing Group)

Onboarded new members and maintained a fleet of 60+ departmental machines using Ansible.

M.S.

Seoul National University

Computer Science and Engineering

• Advisor : Prof. Jaejin Lee
• Thesis: Towards Higher Generative Question-Answering Accuracy: Punctuation Mark Pattern-based Line Filtering on Korean Web Text

B.A.

Seoul National University

Business Administration & Computer Science and Engineering

• Summa Cum Laude
• Best Thesis Paper (College of Business Administration)
• Business thesis : Analysis of IPO Underpricing and After-Market Price Fluctuation
• CSE thesis : Applying Activation Recomputation for CNN Training

Hankuk Academy of Foreign Studies

Humanities and Social Science Course

UDC-VIT: A Real-World Video Dataset for Under-Display Cameras

ICCV 2025 (to appear)

Kyusu Ahn, Jisoo Kim, Hyungyu Lee, Byeonghyeon Ko, Chanwoo Park, and Jaejin Lee.

Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean

arXiv:2510.24150

Chanwoo Park, Suyoung Park, JiA Kang, Jongyeon Park, Sangho Kim, Hyunji M. Park, Sumin Bae, Mingyu Kang, Jaejin Lee

Beyond Line-Level Filtering for the Pretraining Corpora of LLMs

arXiv:2510.24139

Chanwoo Park, Suyoung Park, Yelim Ahn, Jongmin Kim, Jongyeon Park, Jaejin Lee

Enhancing Face Recognition Accuracy for Under-Display Cameras via Image Restoration

SID Display Week 2025 (Distinguished Paper)

Kyusu Ahn, Chanwoo Park, and Jaejin Lee.

Thunder-Tok: Minimizing Tokens per Word in Tokenizing Korean Texts for Generative Language Models

arXiv:2506.15138

Gyeongje Cho, Yeonkyoun So, Chanwoo Park, Sangmin Lee, Sungmok Jung, Jaejin Lee

Integrating Spatial and Frequency Information for Under-Display Camera Image Restoration

arXiv

Kyusu Ahn, Jinpyo Kim, Chanwoo Park, Jisoo Kim, and Jaejin Lee.

Analysis of Large Language Model Performance According to Korean-English Training Data Ratio in Continual Learning

Korea Software Congress 2024

Jinpyo Kim, Gyeongje Cho, Chanwoo Park, Jongwon Park, and Jaejin Lee.

Exploring the Impact of Pre-training Corpora on the Performance of Language Models

Korea Computer Congress 2024

Yujin Jeong, Jaehwan Lee, Chanwoo Park, Donghun Choi, and Jaejin Lee.

UDC-SIT: A Real-World Dataset for Under-Display Cameras

NeurIPS 2023 (Datasets and Benchmarks)

Kyusu Ahn, Byeonghyun Ko, Hyungyu Lee, Chanwoo Park, and Jaejin Lee.

Applying Influence Range to Under-Display Camera Image Restoration

IMID 2023

Kyusu Ahn, Byeonghyun Ko, Hyungyu Lee, Chanwoo Park, and Jaejin Lee.