Daeun(Dana) Lee | UNC Chapel Hill

About Me

Thanks for visiting my website! ✨
I am a 1st-year Ph.D. student at UNC Chapel Hill, MURGe-Lab (Advisor: Prof. Mohit Bansal).
Previously, I was advised by Prof. Jinkyu Kim at Korea University and Prof. Sung Ju Hwang at KAIST.

Research Interests

Faithfulness: OOD Generalization, Evaluation Metrics for Generation
Self-Evolving/Correcting Models: Model-Guided Verification
User-Interactive MLLM: Chat-based MLLM, Interleaved MLLM
Video Generation/Understanding

News

[Aug. 2024] I started PhD journey at the UNC Chapel Hill MURGe-Lab! 🎓
[May. 2024] One 1st author paper got accepted to ICML2024 🇦🇹
[Apr. 2024] One 1st author paper got accepted to CVPRW2024 🇺🇸
[Jan. 2023] One 1st author paper is oral-presented at WACV2023 🏝️
[Dec. 2022] I finished my first research internship at NAVER LABS! 🚙

Publications

ICML

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

Daeun Lee*, Jaehong Yoon*, Sung Ju Hwang

International Conference on Machine Learning (ICML), 2024.

PDF Code

CVPRW

HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization

Daeun Lee, Minhyeok Heo, Jiwon Kim

CVPR Data-Driven Autonomous Driving Simulation Workshop (CVPRW), 2024.

PDF

WACV

Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling

Daeun Lee, Jinkyu Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.

PDF

ECCV

Bridging the Domain Gap towards Generalization in Automatic Colorization

Hyejin Lee, Daehee Kim, Daeun Lee, Jinkyu Kim, Jaekoo Lee

European Conference on Computer Vision (ECCV), 2022.

PDF

Services

Conference Reviewer: CVPR 2022,2024, ECCV 2022,2024, AAAI 2025

Acknowledgement

💐 I have always believed that my achievements and learning are based on collaboration and my great advisers. I really appreciate Mohit Bansal, Jaehong Yoon, Jinkyu Kim, Minhyeok Heo, Sung Ju Hwang, Sungbin Lim.