Hyundong Jin

Email: tuzi04@yonsei.ac.kr

LinkedIn: hyundong-jin-babb60382

Profiles

Research Interests

  • Formal language theory and theoretical foundations of language modeling
  • Controllable generation, model steering, and constrained decoding
  • Reasoning, evaluation, and interpretability of language models

Education

Yonsei University, Seoul, South Korea
Ph.D. student in Department of Computer Science Sep.2024–Present
B.E. in Chemical Engineering and Computer Science (Double Major) Mar.2017–Aug.2024

Experience

Research Intern Jan.2024–Aug.2024
Theory of Computation Lab., Yonsei University, Seoul, South Korea Advisor: Prof. Yo-Sub Han
Research on classification of LLM-paraphrased code
Research Intern Mar.2022–Feb.2023
Big Data Analytics Lab., Yonsei University, Seoul, South Korea Advisor: Prof. Noseong Park
Research on image classification and neural ODEs

Publications

A Regex Minimization Benchmark: A PSPACE-Complete Challenge for Language Models
Hyundong Jin, Joonghyuk Hahn, Yo-Sub Han
Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL), Mar. 2026, Vol. 1, pp. 8020–8048
Detecting code paraphrased by large language models using coding style features
Shinwoo Park, Hyundong Jin, Jeong-won Cha, Yo-Sub Han
Engineering Applications of Artificial Intelligence (EAAI), Dec. 2025, Vol. 162, p. 112454
Mondrian: A Framework for Logical Abstract (Re) Structuring
Elizabeth Grace Orwig, Shinwoo Park, Hyundong Jin, Yo-Sub Han
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 2025, pp. 33663–33678
TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
Hyundong Jin, Sicheol Sung, Shinwoo Park, SeungYeop Baik, Yo-Sub Han
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-findings), Nov. 2025, pp. 33663–33678
Operator-learning-inspired modeling of neural ordinary differential equations
Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Mar. 2024, Vol. 38, No. 10, pp. 11543–11551
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, Noseong Park
Proceedings of the International Conference on Learning Representations (ICLR), Jan. 2024

Skills

Python, Java, C++, C, MATLAB, PyTorch, Transformers