Portrait of Jaehyung Kim

Jaehyung Kim

Assistant Professor
Department of Artificial Intelligence
Yonsei University

jaehyungk@yonsei.ac.kr · wogudehowl@gmail.com

Google Scholar CV

Bio

I am an Assistant Professor in the Department of Artificial Intelligence at Yonsei University, where I lead the Machine and Language Learning Lab (ML3).

My research aims to build AI systems that are both highly capable and aligned with humans. I develop machine learning and natural language processing algorithms, with a focus on large language models and their multimodal extensions. My interests span alignment, personalization, safety, interpretability, adaptation, self-improvement, multimodality, and evaluation, with the goal of making these systems more accurate and reliable in real-world settings.

Previously, I was a postdoctoral researcher at Carnegie Mellon University, working with Yiming Yang. I received my Ph.D. from KAIST under the supervision of Jinwoo Shin. During my Ph.D., I also worked closely with Dongyeop Kang at the University of Minnesota.

For the latest lab news, visit the ML3 homepage.

Work Experience

Awards

  • 2026 SAC Highlight Award, EMNLP
  • 2022 Winner ($5,000), Qualcomm Innovation Fellowship Korea
  • 2021 Silver Prize ($7,000), Samsung Humantech Paper Awards
  • 2021 Winner ($5,000), Qualcomm Innovation Fellowship Korea
  • 2017 3rd Place, ILSVRC (ImageNet Challenge) on Object Detection

Professional Services

Senior Program Committee

  • Area Chair, International Conference on Machine Learning (ICML): 2027
  • Area Chair, Association for Computational Linguistics (ACL) Rolling Review: 2025, 2026
  • Area Chair, International Conference on Learning Representations (ICLR): 2026
  • Area Chair, Neural Information Processing Systems (NeurIPS): 2025, 2026

Conference Reviewer

  • AAAI Conference on Artificial Intelligence (AAAI): 2021, 2022, 2023
  • Association for Computational Linguistics (ACL) Rolling Review: 2022–2025
  • Conference on Computer Vision and Pattern Recognition (CVPR): 2023
  • Conference on Empirical Methods in Natural Language Processing (EMNLP): 2022, 2023
  • International Conference on Learning Representations (ICLR): 2022–2025
  • International Conference on Machine Learning (ICML): 2021–2026
  • Neural Information Processing Systems (NeurIPS): 2021–2024

Journal Reviewer

  • Transactions on Machine Learning Research (TMLR)
  • Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Teaching

2026 Spring

  • Large Language Models (CAS 4133)

2025 Fall

  • Deep Neural Networks (CAS 3201)
  • Limitations and Overcoming Strategies of Large Language Models (AAI 5019)

2025 Spring

  • Large Language Models (CAS 4133)
  • Understanding and Application of Large Language Models (GEK 6217 & GCB 6103)
    Outstanding Teaching Award

2024 Fall

  • Theory and Practice of Deep Learning (AAI 3201)
  • Limitations and Overcoming Strategies of Large Language Models (AAI 5019)

Talks

2026

  1. Aligning LLMs with Individuals and Humanity: From Universal to Personalized Alignment

    Fall Conference, Korean Artificial Intelligence Association

  2. Make System Prompts Matter for Safe LLM: From Decoding to Training

    Department of Electrical Engineering, UNIST

  3. Auditing LLM Judges: From Human-Grounded Bias Analysis to Broader Discovery

    2026 Korea Day @ Microsoft Research Asia

  4. Decoding Algorithms to Attack and Defend LLMs from Jailbreak

    AI Security Workshop, Korea Institute of Information Security & Cryptology

  5. Basics & Recent Approaches for Safer & Better LLM Agent Utilization

    Samsung Display

2025

  1. Limitations of Utilizing Large Language Models for Linguistic Research and Potential Solutions

    Department of Korean Language and Literature, Yonsei University

2024

  1. Beyond the Era of Transformer-based AI Foundation Models

    Samsung Future Technology Research

  2. Designing New Effective Inference Algorithms for Large Language Models

    Ulsan National Institute of Science and Technology (UNIST)

  3. Designing New Effective Inference Algorithms for Large Language Models

    Amazon Artificial General Intelligence (AGI)

2021

  1. Deep Learning with Imbalanced Datasets

    Samsung Electronics Data & Information Technology Center

  2. Multi-aspect Analysis on Data Informativeness

    Summer 2021 Presentation Minnesota NLP Group

2020

  1. Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

    NeurIPS 2020 Social ML in Korea