Curriculum Vitae

Research Interests

• Program analysis and time complexity prediction using large language models
• Specification-driven test case generation and validation
• Contract-satisfying code generation from problem specifications
• Multi-agent debate frameworks for LLM-based reasoning and decision-making

Education

• Integrated MS/PhD in Computer Science, Yonsei University, Seoul, Korea (2024–Present)
  Research: time complexity prediction, test case generation, multi-agent debate for program analysis
• Bachelor's degree in Information and Communication Engineering, Myongji University (2018–2024)

Experience

Theory of Computation Lab, Yonsei University

• Graduate Researcher (2024–Present): Leading projects on time complexity prediction, test case generation, and multi-agent debate for program analysis

Publications

• SLICE: Specification-Level Isolation of Contract Enforcement
  Soohan Lim, Hyundong Jin, Yo-Sub Han^†
  arXiv Preprint 2026
• STAB: Specification-driven Testing for Algorithmic Bottlenecks
  Soohan Lim*, Joonghyuk Hahn*, Hyundong Jin, Yo-Sub Han^†
  arXiv Preprint 2026
• ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
  Soohan Lim*, Joonghyuk Hahn*, Hyunwoo Park, Sang-Ki Ko, Yo-Sub Han^†
  Findings of ACL 2026
• K-SpecDetox: Korean Spectral Energy-based Detection and Detoxification of Dialect Profanity
  Soohan Lim, Sang-Min Choi, Yo-Sub Han
  KCC 2026 (Poster)
• MEC³O: Multi-Expert Consensus for Code Time Complexity Prediction
  Joonghyuk Hahn*, Soohan Lim*, Yo-Sub Han^†
  arXiv Preprint 2025
• K-ToPiC: Korean Dialect Toxicity Polishing with Curriculum Learning-based Span Detection
  Jungin Kim*, Soohan Lim*, Hyeseon Ahn, Sang-Min Choi, Yo-Sub Han^†
  KCC 2025 (Oral Presentation)
• TCProF: Time-Complexity Prediction SSL Framework
  Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim, Soohan Lim, Yo-Sub Han^†
  NAACL 2025 (Oral Presentation)
• CA-DiaL: Curriculum and Attribute-Based Learning for Korean Dialect Translation using LLMs
  Soohan Lim, Joonghyuk Hahn, Hyeseon Ahn, Sang-Min Choi, Yo-Sub Han^†
  KSC 2024 (Poster)

^* co-first authorship; ^† corresponding author.

Skills

• Programming: C/C++, Python
• Tools/Frameworks: Git, PyTorch, TensorFlow, LLM

Advisor

Prof. Yo-Sub Han
Department of Computer Science, Yonsei University
Email: emmous@yonsei.ac.kr