Hoyoon Byun

Ph.D. Student, Department of Statistics and Data Science, Yonsei University
📧 hoyun dot byun at yonsei dot ac dot kr
🌐 MLAI Lab @ Yonsei Univ.

About Me

I am a Ph.D. student in the Department of Statistics and Data Science at Yonsei University, advised by Prof. Kyungwoo Song. My research interests lie in understanding the fundamental limitations of state-of-the-art AI systems and developing principled approaches to overcome them from diverse perspectives, including self-evolving AI, causal representation learning, and domain generalization.

Research Interests

• Self-evolving AI
• Causal Representation Learning
• Domain Generalization

Education

• Yonsei University, Korea – Ph.D. in Statistics and Data Science (2024–Present)
  • Advisor: Kyungwoo Song
• University of Seoul, Korea – M.S. in Artificial Intelligence (2022–2024)
  • Advisor: Jiyoung Jung
  • Co-advisor: Kyungwoo Song (Yonsei University)
• Pukyong National University, Korea – B.S. in Electrical and Semiconductor Engineering (2014–2021)

Publications

Conference

1. Hoyoon Byun Youngjun Choi, Taero Kim, Sungrae Park and Kyungwoo Song, Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models, ICML 2026.
2. Gyeongdeok Seo, Jaeyoon Shim, Mingyu Kim, Hoyoon Byun, Yonghan Jung, Kyungwoo Song, Dissecting Causal Mechanism Shifts via FANS: Function And Noise Separation, ICML 2026.
3. Hoyoon Byun, Sumin Park, Jinho Kang, Hyeonjeong Lee, Minseong Kim, Doosik Kim, Kwang-Young Kim and Kyungwoo Song, CBPE: Causal-aware Blood Pressure Estimation with Multimodal Data, ACM SAC 2026.
4. Hoyoon Byun, Gyeongdeok Seo, Joonseong Kang, Taero Kim, Jihee Kim, Kyungwoo Song, “CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization”, NeurIPS 2025.
5. Hoyoon Byun, Minhoi Park, Seolah Kim, Eunbi Kim, Kyungwoo Song,
   “Exploring the Potential of Foundation Models as Reliable AI Contact Centers”, KDD Datasets and Benchmarks Track 2025.
6. Sungjun Lim, Jeyoon Yeom, Sooyon Kim, Hoyoon Byun, Jinho Kang, Yohan Jung, Jiyoung Jung, Kyungwoo Song, “Flat Posterior Does Matter For Bayesian Model Averaging”, UAI 2025
7. Kangjun Noh, Baekryun Seong, Hoyoon Byun, Youngjun Choi, Sungjin Song, and Kyungwoo Song,
   “LBC: Language-Based-Classifier for Out-Of-Variable Generalization”, NAACL 2025.
8. Hakyung Lee, Keon-Hee Park, Hoyoon Byun, Jeyoon Yeom, Jihee Kim, Gyeong-Moon Park, Kyungwoo Song,
   “CED: Comparing Embedding Differences for Detecting Out-of-Distribution and Hallucinated Text”, EMNLP 2024 Findings.
9. Heeyoung Lee*, Hoyoon Byun*, Changdae Oh, JinYeong Bak, Kyungwoo Song,
   “Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments”, ECAI 2024.
10. Changdae Oh, Junhyuk So, Hoyoon Byun, YongTaek Lim, Minchul Shin, Jong-June Jeon, Kyungwoo Song,
    “Geodesic Multi-Modal Mixup for Robust Fine-tuning”, NeurIPS 2023.

Journal

1. Jinho Kang, Hoyoon Byun, Taero Kim, Jiyoung Jung, Kyungwoo Song, “Multi-query frequency prompting for physiological signal domain adaptation”, Knowledge-Based Systems
2. Seyun Bae, Hoyoon Byun, Changdae Oh, Yoon-Sik Cho, Kyungwoo Song,
   “Graph perceiver IO: A general architecture for graph-structured data”, Pattern Recognition.
3. Hoyoon Byun, Sungjun Lim, and Kyungwoo Song,
   “GFML: Gravity Function for Metric Learning”, Engineering Applications of Artificial Intelligence (EAAI).
4. Jeyoon Yeom, Hakyung Lee, Hoyoon Byun, Yewon Kim, Jeongeun Byun, Yunjeong Choi, Sungjin Kim, Kyungwoo Song,
   “TC-Llama 2: Korean Large Language Model for Technology-Commercialization Data”, Journal of Big Data (SCIE).

(*Equal Contribution)

Under Review

• “Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models” Hoyoon Byun, Youngjun Choi, Taero Kim, Sungrae Park, Kyungwoo Song
• “MIDUS: Memory-Infused Depth Up-Scaling”, Taero Kim, Hoyoon Byun, Youngjun Choi, Sungrae Park, Kyungwoo Song

Workshops

• “A Double-Edged Sword: Benchmarking the Trade-off Between Bias Mitigation and Helpfulness of LLM Guardrails in Finance”, FinAI Workshop in CIKM 2025
• “Exploring the Potential of Foundation Models as Reliable AI Contact Centers”, IJCAI 2024 Workshop (Oral Presentation)
• “H-Consistency Bounded Critic for Enhancing Retrieval-Augmented Generation”, IJCAI 2024 Workshop
• “LBC: Language-Based-Classifier for Out-Of-Variable Generalization”, IJCAI 2024 Workshop (Oral Presentation)
• “Flat Posterior For Bayesian Model Averaging”, IJCAI 2024 DSO Workshop

Experience

• Visiting Researcher, Australian National University (July, 25, 2025 - Aug, 22, 2025)
  Short-term research visit under supervision of Prof. Lexing Xie.
• Course Assistant, ML for RecSys, Naver Boostcamp AI Tech (The 8th class) (July, 28, 2025 – Present)
  Developed practice materials and evaluation problems
• Course Assistant, ML for RecSys, Naver Boostcamp AI Tech (The 7th class) (July, 01, 2024 – Sep, 09, 2024)
  Developed practice materials and evaluation problems
• Teaching Assistant, Linear Algebra with Applications, University of Seoul (Sep. 2023 – Dec. 2023)

Research Projects

• Developing Training Methods for LLMs that Adapt Well to New Knowledge (Mar. 2025 - Present)
• AI-Based Personalized Blood Pressure Estimation (Apr. 2024 – Dec. 2024)
• Generative AI for Smart Consultation (Jul. 2023 – Dec. 2023)
• Multi-category Mapping between Heterogeneous Data (Mar. 2023 – Oct. 2023)
• Trustworthy AI and Causal Inference (Jun. 2022 – Mar. 2024)
• Personalized Fair Job Recommendation Algorithm (Jul. 2022 – Dec. 2022)
• Epidemiological Relevance Evaluation for Vaccination Reactions (Mar. 2022 – Dec. 2023)
• Financial and Telecommunication Data Analysis (Mar. 2022 – May. 2022)

Technical Skills

• Programming Languages: Python, R, C++
• Deep Learning Frameworks: PyTorch, TensorFlow

Additional Information

• Military Service (May. 2015 – Feb. 2017)
  • Auxiliary Police, Army Sergeant (Honorable Discharge)