Jinho Park | Home

About

Hello👋🏻, I'm a M.S. student in Language & Knowlege Lab at KAIST Kim Jaechul Graduate School of AI. I am grateful to be advised by Minjoon Seo. Before my Master's, I earned a B.S. in Computer Science at KAIST with a minor in Electrical Engineering in 2024.

I am an AI Engineer with a strong research background in Natural Language Processing (NLP), currently focusing on building evaluation, training, and data generation pipelines for large-scale language and vision-language models. My interests lie in understanding the underlying mechanisms that drive model behavior, particularly how language models acquire and use knowledge during training, and in improving reasoning and generalization through systematic evaluation and data-centric analysis. Ultimately, I am drawn to work that bridges research on model behavior and large-scale model development, enabling reliable model improvements through scalable and well-designed AI systems.

For details, refer to my Curriculum Vitae (CV).

Publications

Most recent publications on Google Scholar.
^‡ indicates equal contribution.

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

Hoyeon Chang*, Jinho Park*, Hanseul Cho, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, Minjoon Seo

ICLR 2026

Paper Code Bib

 
                  
 @article{chang2025coverage,
 title={The Coverage Principle: A Framework for Understanding Compositional Generalization},
 author={Chang, Hoyeon and Park, Jinho and Cho, Hanseul and Yang, Sohee and Ko, Miyoung and Hwang, Hyeonbin and Won, Seungpil and Lee, Dohaeng and Ahn, Youbin and Seo, Minjoon},
 journal={arXiv preprint arXiv:2505.20278},
 year={2025}
 }

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

Seongyun Lee*, Seungone Kim*, Minju Seo, Yongrae Jo, Dongyoung Go, Hyeonbin Hwang, Jinho Park, Xiang Yue, Sean Welleck, Graham Neubig, Moontae Lee, Minjoon Seo

ICLR 2026

Paper Code Bib

 
                  
 @article{lee2025cot,
 title={The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think},
 author={Lee, Seongyun and Kim, Seungone and Seo, Minju and Jo, Yongrae and Go, Dongyoung and Hwang, Hyeonbin and Park, Jinho and Yue, Xiang and Welleck, Sean and Neubig, Graham and others},
 journal={arXiv preprint arXiv:2505.10185},
 year={2025}
 }

How language models extrapolate outside the training data: A case study in Textualized Gridworld

Doyoung Kim, Jongwon Lee, Jinho Park, Minjoon Seo

NeurIPS 2024 Compositional Learning Workshop

Paper Code Bib

 
                  
 @article{kim2024cognitive,
 title={Cognitive Map for Language Models: Optimal Planning via Verbally Representing the World Model},
 author={Kim, Doyoung and Lee, Jongwon and Park, Jinho and Seo, Minjoon},
 journal={CoRR},
 year={2024}
 }

How Do Large Language Models Acquire Factual Knowledge During Pretraining?

Hoyeon Chang, Jinho Park, Seonghyeon Ye, Sohee Yang, Youngkyung Seo, Du-Seong Chang, Minjoon Seo

NeurIPS 2024

Paper Code Bib

 
                  
 @inproceedings{chang2024large,
 title={{How do large language models acquire factual knowledge during pretraining?}},
 author={Chang, Hoyeon and Park, Jinho and Ye, Seonghyeon and Yang, Sohee and Seo, Youngkyung and Chang, Du-Seong and Seo, Minjoon},
 booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}
 }

Projects

Selected
All

Shoulder of Giants
Reimplement the paper (3D AI)

HOMEY
Mobile App optimizing home environment

Training Efficient Boosting Algorithm
Predict fake import declarations using LightGBM

SPARCS Taxi
Development on-campus taxi carpool App using React.js and Javascript

Developing an in-house analytics page
Event log analysis page using Vue.js and Spring

Kaggle Competition
Detect distracted driver using Deep Learning

Creating Song Lyrics System
Using Char-RNN model (Deep Learning)

Shoulder of Giants
Reimplement the paper (3D AI)

HOMEY
Mobile App optimizing home environment

Training Efficient Boosting Algorithm
Predict fake import declarations using LightGBM

SPARCS Taxi
Development on-campus taxi carpool App using React.js and Javascript

SPARCS SSO
Manage integrated login system using Django REST framework and MySQL

Developing an in-house analytics page
Event log analysis page using Vue.js and Spring

Kaggle Competition
Detect distracted driver using Deep Learning

Creating Song Lyrics System
Using Char-RNN model (Deep Learning)

Vitæ

LG AI Research Sep 2025 - now

EXAONE team AI Engineer Intern
Improving VLM evaluation and contributing to the development of the next version of the EXAONE model
KAIST Mar 2024 - now

M.S. Student
KAIST Language & Knowledge Lab
(Advisor: Minjoon Seo)
KAIST Mar 2023 - Feb 2024

Undergraduate Research Intern
Language & Knowledge Lab
(Advisor: Minjoon Seo)
Growdle Sep 2022 - Feb 2023

AI R&D Team Intern
Utilize Retrieval-based Method to Solve Dialogue Summarization Task
KAIST Jun 2022 - Aug 2022

Undergraduate Research Intern
Prosys Lab
(Advisor: Kihong Heo)
KAIST Dec 2021 - Jun 2022

Undergraduate Research Intern
User & Information Lab
(Advisor: Alice Oh)
SAMSUNG Electronics Jul 2021 - Aug 2021

Develop Intern
Development Event Log Analysis Web Page
KAIST Mar 2017 - Feb 2024

B.S. Student
Computer Science
minored in Electrical Engineering

Teaching Experiences

KAIST Mentor, Summer 2024, 2024 Seocho AI College Project, KAIST ITA
Teaching Assistant, Spring 2025, 2025 KAIST SW Education Center Military AI/SW Course, KAIST ITA
Teaching Assistant, Spring 2025, 2025 Seocho AI College Basic & Advanced Course, KAIST ITA