Jaewoo Lee | UNC Chapel Hill

About Me

Thanks for visiting my website!😄
I am an incoming Ph.D. student at UNC Chapel Hill, MURGe-Lab (Advisor: Prof. Mohit Bansal). Previously, I collaborated with Prof. Boyang Li at NTU. I had an internship at the MIT Media Lab, where I had the opportunity to collaborate with Prof. Paul Liang and Prof. Yi R. Fung. I received a M.S. degree in Artificial Intelligence at KAIST in Aug 2024 (Prof. Sung Ju Hwang) and a B.S. degree in Electrical Engineering at KAIST in Feb 2023 (Summa Cum Laude Award).

Research Interests

Multimodal: Vision-Language, Audio-Visual, Interleaved modalities
Efficiency in data & algorithms: Data selection, Continual learning, Curriculum learning
Efficiency in systems: Retrieval-Augmented Generation, Information retrieval
Efficiency in architectures: Mixture of Experts, Token reduction, Model Compression
Interpretability: Interpretable LLM and MLLM, Attribution methods

News

[Aug. 2025] I’ll be starting my PhD journey at the UNC Chapel Hill MURGe-Lab!
[Jun. 2025] One paper got accepted to VecDB Workshop @ ICML 2025
[Apr. 2025] One paper got accepted to ACL Findings 2025 🇦🇹
[Feb. 2025] I finished my research internship at MIT Media Lab!
[Aug. 2024] One paper got accepted to EMNLP 2024 🇺🇸
[Jun. 2024] I finished my research collaboration at NTU!
[May. 2024] One paper got accepted to ICML 2024 🇦🇹

Publications

(* denotes the equal contribution and ^ denotes the equal advising)

ACL Findings

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote, Sandeep Polisetty, Yi R. (May) Fung, Paul Pu Liang

Annual Meeting of the Association for Computational Linguistics, Findings Long paper (ACL Findings), 2025.

PDF Code

ICML Workshop

Unified Multimodal Interleaved Document Representation for Retrieval

Jaewoo Lee*, Joonho Ko*, Jinheon Baek*, Soyeong Jeong, Sung Ju Hwang

VecDB Workshop @ International Conference on Machine Learning (ICML Workshop), 2025.

PDF

EMNLP

Concept-skill Transferability-based Data Selection for Large Vision-Language Models

Jaewoo Lee, Boyang Li^, Sung Ju Hwang^

Conference on Empirical Methods in Natural Language Processing, Main conference Long paper (EMNLP), 2024.

PDF Code

ICML

STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment

Jaewoo Lee*, Jaehong Yoon*, Wongjae Kim, Yunji Kim, Sung Ju Hwang

International Conference on Machine Learning (ICML), 2024.

PDF Code Project Page

ICSV

Sound-based drone fault classification using multitask learning

Wonjun Yi, Jung-Woo Choi, Jaewoo Lee

International Congress on Sound and Vibration (ICSV), 2023.

PDF Dataset

Educations

2023.03 - 2024.08, M.S. in Artificial Intelligence. KAIST.
- Thesis: Efficient Training Techniques for Multimodal Learning (PDF)
- A half-year early graduation.
2020.03 - 2023.02, B.S. in Electrical Engineering. KAIST.
- Summa Cum Laude
- One-year early graduation.

Research Experiences

2024.11 - 2025.02, Research Intern, MIT Media Lab, United States.
2024.08 - 2025.03, AI Researcher, DeepAuto, South Korea.
2024.01 - 2024.06, Research collaborator, NTU, Singapore.
2023.03 - 2024.08, Master degree Student, MLAI Lab, KAIST, South Korea.
2021.09 - 2022.06, Research Intern, Smart Sound Systems Lab, KAIST, South Korea.
2021.06 - 2021.08, Research Intern, Urban Robotics Lab, KAIST, South Korea.

🎖 Honors and Awards

KAIST Summa Cum Laude Award, Feb. 2023
National Scholarship for Science & Engineering, Sep. 2022 - Feb. 2023
Encouragement Award for the Undergraduate Research Program, Aug. 2022
KAIST Dean’s List (College of Engineering), Aug. 2022
KAIST Dean’s List (School of Freshman), Aug. 2020