About Me
I am a Ph.D. student in Department of Computer Sciences at the University of Wisconsin-Madison, advised by Prof. Sharon Yixuan Li. Before joining Sharon’s group, I obtained my MS degree in Artificial Intelligence at the University of Seoul under supervision of Prof. Kyungwoo Song and Prof. Jiyoung Jung. I had the privilege of working with Zhi-Qi Cheng, Alexander Hauptmann, and David Mortensen during visiting at Carnegie Mellon University, and internship at NAVER AI Lab allows me to be advised by Dongyoon Han and Sangdoo Yun.
I am broadly interested in machine learning fundamentals and AI safety & reliability. Recently, I have explored the intersection of robustness under distribution shift and efficient adaptation of large-scale foundation models.
📢 Actively seeking a 2025 summer research internship (in US or outside)!
💭 Interest & Expertise: robustness under distribution shifts, efficient adaptation of foundation models, reliability of multimodal large language models, model merging, and machine learning fundamentals – [CV link]
📩 Feel free to contact me if you find any alignment :)
Publication
(conference, journal, and * denotes equal contribution)
DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
[paper][code]
Changdae Oh, Yixuan Li, Kyungwoo Song, Sangdoo Yun, Dongyoon Han
NeurIPS 2024, Workshop on Adaptive Foundation ModelsTowards Calibrated Robust Fine-Tuning of Vision-Language Models
Changdae Oh*, Hyesu Lim*, Mijoo Kim, Dongyoon Han, Sangdoo Yun, Jaegul Choo, Alexander Hauptmann, Zhi-Qi Cheng, Kyungwoo Song
[paper] [code]
NeurIPS 2024TC-BERT: Large-scale Language Model for Korean Technology Documents
[paper] [code]
Taero Kim*, Changdae Oh*, Hyeji Hwang*, Eunkyeong Lee, Yewon Kim, Yunjeong Choi, Sungjin Kim, Hosik Choi, Kyungwoo Song
The Journal of Supercomputing 2024Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer
[paper]
Haeji Jung, Changdae Oh, Jooeon Kang, Jimin Sohn, Kyungwoo Song, Jinkyu Kim, David R. Mortensen
EMNLP 2024, Multilingual Representation Learning WorkshopPerturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments
Hee-young Lee*, Hoyoon Byun*, Changdae Oh, JinYeong Bak, Kyungwoo Song
[paper]
ECAI 2024First Step for Theoretical and Practical Foundations of Robust Visual Prompting
Gyeongdeok Seo*, Changdae Oh*, Kyungwoo Song
IJCAI 2024, The Trustworthy AI WorkshopLanguage Model-guided Student Performance Prediction with Multimodal Auxiliary Information
Changdae Oh, Minhoi Park, Sungjun Lim, Kyungwoo Song
[paper] [code]
Expert Systems with Applications 2024Bibimbap: Pre-trained Models Ensemble for Domain Generalization
Jinho Kang, Taero Kim, Yewon Kim, Changdae Oh, Jiyoung Jung, Rakwoo Chang, Kyungwoo Song
[paper] [code]
Pattern Recognition 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Changdae Oh, Mijoo Kim, Hyesu Lim, Junhyeok Park, Euiseog Jeong, Zhi-Qi Cheng, Kyungwoo Song
[paper]
NeurIPS 2023, Workshop on Distribution ShiftsGeodesic Multi-Modal Mixup for Robust Fine-tuning
Changdae Oh*, Junhyuk So*, YongTaek Lim, Hoyoon Byun, Minchul Shin, Jong-June Jeon, Kyungwoo Song
[paper] [code]
NeurIPS 2023Robust Contrastive Learning with Dynamic Mixed Margin
[paper] [code]
Junhyuk So*, YongTaek Lim*, Yewon Kim*, Changdae Oh, Kyungwoo Song
IEEE Access 2023BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning
[paper] [code]
Changdae Oh, Hyeji Hwang, Hee-young Lee, YongTaek Lim, Geunyoung Jung, Jiyoung Jung, Hosik Choi, Kyungwoo Song
CVPR 2023Learning Fair Representation via Distributional Contrastive Disentanglement
[paper] [code]
Changdae Oh, Heeji Won, Junhyuk So, Taero Kim, Yewon Kim, Hosik Choi, Kyungwoo Song
KDD 2022
Preprints
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
[paper]
Changdae Oh, Gyeongdeok Seo, Geunyoung Jung, Zhi-Qi Cheng, Hosik Choi, Jiyoung Jung, Kyungwoo SongEnhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
[paper]
Sangyoun Lee, Juho Jung, Changdae Oh, Sunghee Yun
- Graph Perceiver IO: A General Architecture for Graph Structured Data
[paper]
Seyun Bae, Hoyoon Byun, Changdae Oh, Yoon-Sik Cho, Kyungwoo Song
Education
Ph.D. in Computer Science, University of Wisconsin-Madison
advisor: Prof. Sharon Yixuan Li
Sep. 2024 ~ PresentM.S. in Artificial Intelligence, University of Seoul
advisor: Prof. Kyungwoo Song and Prof. Jiyoung Jung
Mar. 2022 - Aug. 2024B.S. in Statistics, University of Seoul
Mar. 2016 - Feb. 2022
Experience
- Research Intern, NAVER AI Lab
Mentor: Dongyoon Han and Sangdoo Yun, Apr. 2023 ~ Aug. 2024 - Visiting Student / Collaborator, Carnegie Mellon University
Mentor: Zhi-Qi Cheng, Sep. 2023 ~ Feb. 2024
Academic Services
- Conference Reviewer: ICLR’25, AAAI’25, NeurIPS’24, CVPR’24
- Conference Volunteer: NeurIPS’24, KDD’22