Research Highlights

  • arXiv'25 / TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents / GitHub / 요약
  • arXiv'25 / AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection / GitHub / 요약
  • IJCAI'25 / LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming / GitHub / 요약
  • NAACL'25 / TCProF: Time-Complexity Prediction SSL Framework / GitHub / summary / 요약
  • ACL'25 / KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis / GitHub / 요약
  • arXiv'25 / Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code / GitHub / 요약
  • arXiv'25 / Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features / GitHub / 요약
  • arXiv'25 / URECA: The Chain of Two Minimum Set Cover Problems exists behind Adaptation to Shifts in Semantic Code Search / 요약
  • Coling'25 / Analyzing Offensive Language Dataset Insights from Training Dynamics and Human Agreement Level / GitHub / 요약
  • arXiv'24 / CodeComplex: Dataset for the Worst-Case Time Complexity Prediction / GitHub / summary / 요약
  • arXiv'24 / A Framework for Quantum Finite-State Languages with Density Mapping / GitHub


  • We have one paper (Pattern Mining under Simon's Congruence) accepted for DLT 2025, which will be held in Korea for the first time! Congrats, Sungmin.
  • We have one paper (KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis) accpeted for ACL 2025. Well done, Shinwoo, Shubin, Do-Kyung---especially, Shubin was an undergrad intern in our lab, AMAZING!
  • Our "LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming " paper is accepted for IJCAI 2025. Good job, Sicheol. This is joint work with Prof. Sang-Ki Ko's group from University of Seoul.
  • Our "TCProF: Time-Complexity Prediction SSL Framework" paper is accepted for NAACL 2025. A more detail info will be updated soon. Congrats Joonghyuk, Hyeseon, Jungin and Soohan.
  • Our "Impact of Large Language Models of Code on Fault Localization" paper is accepted for ICST 2025. This is joint work with Prof. Hyeonseung Im's group from Kangwon National University.
  • Our "Analyzing Offensive Language Dataset Insights from Training Dynamics and Human Agreement Level" paper is accepted for COLING 2025. Congrats Do-Kyung and Hyeseon.
  • We have one paper accepted for CIAA 2024; Benchmarking Regular Expression Matching. This is joint work with Prof. van der Merwe (Stellenbosch, South Africa). Good job, Sicheol. He will visit the research group of Prof. van der Merwe during the fall semester and continue our joint research.
  • We have two papers accepted for DLT 2024; Approximate Cartesian Tree Pattern Matching and Universal Rewriting Rules for the Parikh Matrix Injectivity Problem. The second paper is joint work with Prof. Salomaa (Queen's, Canada). Congrats Ingyu, Joonghyuk and Sungmin!
  • 휴먼-AI 협업 프로그래밍 플랫폼 과제 2단계가 시작되었습니다. 기간은 2023.03 ~ 2026.02 입니다.
  • We have one paper accepted for DCFS 2023; Existential and Universal Width of Alternating Finite Automata. This is joint work with Prof. Salomaa (Queen's, Canada) and Prof. Ko (KNU, South Korea).
  • We have two papers accepted for DLT 2023; Weak Inverse Neighborhood of Languages and On the Simon's Congruence Neighborhood of Languages. Good job, Hyunjoon and Sungmin! Indeed we are a language research group.
  • Our "Contrastive Learning with Keyword-based Data Augmentation for Code Search and Code Question Answering" paper is accepted for EACL 2023. Congrats Shinwoo and Youngwook.
  • Our "Automated Grading of Regular Expressions" paper is accepted for ESOP 2023. Good job, Youngwook. This is joint work with Prof. Sang-Ki Ko's group from Kangwon National University.


    RESEARCH INTERESTS


    Contact Information
    School of Computing, Yonsei University
    50 Yonsei-Ro, Seodaemun-Gu, Seoul 03722, Republic of Korea
    Email: emmous [at] yonsei [dot] ac [dot] kr

    Last updated 2025/4/8