Jungin Kim

jungin.jpg

Master Student @ToC Lab

Seoul, South Korea

I am a master’s student at Yonsei University, Graduate School of Computer Science. I focus on applying language model techniques to real-world problems that require security, personalization, and ethical sensitivity. My work includes developing watermarking methods for detecting AI-generated code, designing recommender systems based on user behavior, and building NLP tools that mitigate harmful or biased content. I aim to bridge AI research with practical systems that are secure, transparent, and user-centric.

Connect

CV & Portfolio

Publications

  • Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code [arXiv]
    Jungin Kim, Shinwoo Park, Yo-Sub Han
    Under Review

  • K-ToPiC: Korean Dialect Toxicity Polishing with Curriculum Learning-based Span Detection [KCC 2025]
    Jungin Kim, Soohan Lim, Hyeseon Ahn, Sang-Min Choi, Yo-Sub Han
    Accepted to KCC 2025

  • CodeComplex: A Time-Complexity Dataset for Bilingual Source Codes [EMNLP 2025]
    Seung-Yeop Baik, Joonghyuk Hahn, Jungin Kim, Mingi Jeon, Yo-Sub Han, Sang-Ki Ko
    Accepted to findings of EMNLP 2025

  • TCProF: Time-Complexity Prediction SSL Framework [NAACL 2025]
    Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim, Soohan Lim, Yo-Sub Han
    Accepted to NAACL 2025

  • SharedCon: Implicit Hate Speech Detection using Shared Semantics [ACL 2024 Findings]
    Hyeseon Ahn, Youngwook Kim, Jungin Kim, Yo-Sub Han
    Accepted in Findings of ACL 2024