Thanks for visiting my website! โจ
I am an incoming CS PhD student at UNC-Chapel Hill, MURGe-Lab (Advisor: Prof.Mohit Bansal).
Before starting PhD, I was advised by Prof.Jinkyu Kim at Korea University and Prof.Sung Ju Hwang at KAIST.
My ultimate research goal aligns with making User-Interactive AI that can help underrepresented people all around the world. I enjoyed my undergraduate research journey focusing on Autonomous Driving and Out-of-Distribution Generalization problems. Autonomous Driving was also aligned with my ultimate research goal since it is an impactful technology for every person. Here is my CV.
๐ญ My current research interests include
- User-Interactive Multimodal
- Faithfulness
- Out-of-Distribution Generalization
๐ฅ News
- 2024.06: ย ๐ซ Travel Grant from ICMLโ24 Organizers!
- 2024.05: ย ๐ One paper got accepted to ICMLโ24 ย
- 2024.04: ย ๐ One paper got accepted to CVPRWโ24 ย
- 2024.03: ย ๐ I received BE degree at KU and will start PhD journey at the University of North Carolina at Chapel Hill MURGe-Lab!
- 2023.03: ย ๐ I started my new research journey at KAIST MLAI LAB (Under the supervision of Prof. Sung Ju Hwang) ย
- 2023.01: ย ๐ One paper is oral-presented at WACVโ23 ย
- 2022.12: ย ๐ I finished my first research internship at NAVER LABS well ๐ ย
- 2022.10: ย ๐ One paper is presented at ECCVโ22 ย
๐ Publications
![sym](images/becotta_v2.png)
![sym](images/hdmap_v2.png)
- HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization [paper]
- Daeun Lee, Minhyeok Heo, Jiwon Kim
- This work was done at NAVER LABS.
![sym](images/wacv23.png)
- Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling [paper]
- Daeun Lee, Jinkyu Kim
- This work was done at the Korea University VAI Lab (collaborated with Hyundai Motor).
![sym](images/eccv22.png)
-
Bridging the Domain Gap towards Generalization in Automatic Colorization [paper]
- Hyejin Lee, Daehee Kim, Daeun Lee, Jinkyu Kim and Jaekoo Lee
- This work was done at the Korea University VAI Lab.
![sym](images/traj.png)
-
Trajectory Prediction by Clustering Human Interactions at Multiple Scales
- Chiho Choi*, Daeun Lee*, Srikanth Malla, Sangjae Bae, Jinkyu Kim.
- This work was done at the Korea University VAI Lab (collaborated with Honda Research).
๐ Educations
- 2024.08 - 2029.05 (expected), Ph.D. in Computer Science. UNC-Chaple Hill.
- 2019.03 - 2024.02, B.E. in Statistics. Korea University. (GPA: 4.0/4.5)
๐ป Research Experiences
-
2024.03 - current, Contract Researcher, MLAI Lab, KAIST, South Korea.
- 2023.03 - 2024.02, Research Intern, MLAI Lab, KAIST, South Korea.
- Under the supervision of Prof. Sung Ju Hwang
- 2022.07 - 2022.12, Research Intern, NAVER LABS, South Korea.
- Autonomous Driving Perception team
- 2021.06 - 2022.12, Research Intern, VAI Lab, Korea Univ, South Korea.
- Under the supervision of Prof. Jinkyu Kim
- 2021.01 - 2021.02, Data Analyst Intern, Mirae Asset Securities, South Korea.
๐ Honors and Awards
- 2024.06, Travel Grant from ICML2024 Organizers
- 2020 - 2024, Special Scholarship for outstanding students from Korea University.
- 2021.12, 5st place, ICT Autonomous Driving Project
- 2021.05, 2nd place, Digital Innovation Big Data Contest
- 2020.12, 1st place, Financial Big Data Festival
- 2020.05, TOP 2%, KAKAO ARENA
๐ Academic Services
- Reviewer : CVPR 2022,2024, ECCV 2022,2024
- Volunteer : ICML 2024
๐ Acknowledgement
I always believe my achievements and learning are from my great advisers and collaboration.
I really appreciate Jinkyu Kim, Jaehong Yoon, Minhyeok Heo, Sung Ju Hwang, Sungbin Lim.