The MOAI Lab focuses on foundation models that orchestrate multiple modalities, including vision, language, and physical sensors.
Our research spans two main areas:
1. AI Foundation – developing core algorithms to advance foundation models
2. AI Application – leveraging foundation models to solve real-world problems
Some might say MOAI stands for “Mo’s AI Lab.”
1. Structural Priors for Effective Learning
Encode domain-specific structures to improve performance and interpretability
- Visual structure (image):
InstaGAN (ICLR'19), OACon (NeurIPS'21), OAMixer (CVPRW'22), CAST (ICLR'24), SHED (tbd), F-CAST (tbd)
- Temporal structure (video, language):
DIGAN (ICLR'22), HOMER (ICLR'24), Simba (TMLR'25)
- Structured reasoning (gen models):
SuRe (ICLR'24), PRIS (tbd)
- Physical structure (robotics):
EIT-NN (IROS'19), EIT-NN-v2 (T-RO'21)
- Relational structure (graph, table):
LoGe (ICMLW'21), DPM-SNC (NeurIPS'23)
2. Statistical Priors for Reliable Learning
Estimate and leverage dataset statistics to improve robustness and generalization
- Robust representation (outlier, etc):
CSI (NeurIPS'20), MASKER (AAAI'21), RoPAWS (ICLR'23)
- Reliable generation (fairness, etc.):
GOLD (NeurIPS'19), FICS (TMLR'23), GFG (tbd)
- Extension to novel domains & contexts:
FreezeD (CVPRW'20), S-CLIP (NeurIPS'23), OAK (CVPR'25), ZEPA (tbd)
- Analyzing & leveraging foundation models:
B2T (CVPR'24), PDS (tbd), Idis (tbd)
- Efficient model design:
Graduate students
▪︎ Myeongsoo Kim (BS, POSTECH): Diffusion models
▪︎ Suchan Lee (BS, POSTECH): Language models
▪︎ Seunghyun Jang (BS, SNU): Vision-language models
Interns
▪︎ We are organizing an undergrad AI study group. Please reach out if you’d like to join!
During my PhD and postdoc, I supported several talented students in successfully completing their first-author projects.
▪︎ Byeongju Woo (RS @ ADD). Mentored during postdoc, working in progress.
▪︎ Seung-Hyun Lee (PhD @ UMich). Mentored during postdoc, working in progress.
▪︎ Zilin Wang (PhD @ UMich). Mentored during postdoc, paper accepted at CVPR'25.
▪︎ Woomin Song (PhD @ KAIST). Mentored during PhD, papers accepted at ICLR'24 and TMLR'25.
▪︎ Younghyun Kim (MS @ KAIST). Mentored during PhD, paper accepted at CVPR'24 (highlight).
▪︎ Hyunwoo Kang (MS @ KAIST). Mentored during PhD, papers accepted at NeurIPS'21 and CVPRW'22.
▪︎ Seung-Jun Moon (MS @ KAIST). Mentored during PhD, paper accepted at AAAI'21.
