Lee, Hyun

I am a researcher @ AI Research Center, Samsung Advanced Institute of Technology (SAIT). I received M.S. in EE at POSTECH advised by Prof. Tae-Hyun Oh.
I am interested in multimodal learning, LLMs, generative models, and data-centric AI.

E-mail  /  LinkedIn  /  Google scholar  /  Github  / 

profile photo
Publications
VLM’s Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models
Nam Hyeon-Woo, Moon Ye-Bin, Wonseok Choi, Lee Hyun, Tae-Hyun Oh
preprint
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models
Lee Hyun*, Kim Sung-Bin*, Seungju Han, Youngjae Yu, Tae-Hyun Oh
NAACL, 2024
A Large-Scale 3D Face Mesh Video Dataset Via Neural Re-Parameterized Optimization
Kim Youwang, Lee Hyun, Kim Sung-Bin, Suekyeong Nam, Janghoon Joo, Tae-Hyun Oh
Transactions on Machine Learning Research (TMLR), 2024
LaughTalk: Expressing 3D Talking Head Generation with Laughter
Kim Sung-Bin, Lee Hyun, Dahye Hong, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
Multimodal Laughter Reasoning with Textual Audio-Visual Representation
Lee Hyun, Kim Sung-Bin, Suengju Han, Youngjae Yu, Tae-Hyun Oh
ICCV workshop, 2023
Spatio-Temporally Consistent Face Mesh Reconstruction on Videos
Kim Youwang, Lee Hyun, Kim Sung-Bin, Suekyeong Nam, Janghoon Joo, Tae-Hyun Oh
CVPR workshop, 2023
ComMU: Dataset for Combinatorial Music Generation with LLM
Lee Hyun, Teahyun Kim, Hyolim Kang, Minjoo Ki, Hyeonchan Hwang, Kwanho Park, Sharang Han, Seon Joo Kim
NeurIPS, 2022
project page
AI-Based Dental Prostheses Fabrication Using Generative Adversarial Networks
Lee Hyun, Nalinh Thoummala, HyukJun Park, SeoungHyun Ham, Jiwoong Yu, JangHoon Hwang, SungHwan Kim
Quantitative Bio-Science(KCI), 2021
Education
  • Master in Electrical Engineering, POSTECH (2024), Korea
  • Bachelor in Statistics (minor in computer engineering), Konkuk Univ. (2022), Korea
Work Experiences
  • Research engineer, SAIT, 3.2024 - present
  • Machine learning engineer, POZAlabs, 2.2021 - 1.2022
  • Military service, discharged as sergeant, Vanguard Unit, Republic of Korea Army, 3.2017 - 12.2018
Teaching Experiences
Invited Talk
  • Multimodal Video Reasoning with Language Model, ICCV, 10.2023
  • Music Generation with Language Model, Modulabs, 1.2023
  • AI Research and Graduate School, Konkuk Univ., 6.2022
Project
  • Multimodal representation learning on 3D face videos with speech, KRAFTON, 2.2022 - 1.2024

Template based on Jon Barron's website.