Sangwoo Mo - Group

Multimodal Orchestration of Artificial Intelligence (MOAI) Lab 🗿

The MOAI Lab aims to build foundation models that orchestrate multiple modalities, including vision, language, and physical interaction. Our research spans two main areas: 1) AI Foundation, developing core deep learning algorithms, and 2) AI Application, applying foundation models to solve real-world problems. Some might say MOAI stands for “Mo’s AI Lab”.

We are currently focusing on the following research directions. If you are interested in these projects, please contact us for an internship:

1. Enhancing multimodal models by incorporating structures

- Multimodal models grounded in mid-level representations (follow-up of CAST and SHED)

- Multimodal models for handling ad-hoc categories (follow-up of OAK)

- Exploring other priors in domains such as language, audio, and robotics

2. Extending multimodal models to vertical domains

- Multimodal understanding and generation for specialist domains (follow-up of S-CLIP)

- Measuring uncertainties in multimodal domains (follow-up of CSI and RoPAWS)

- Identifying and mitigating biases in multimodal models (follow-up of B2T)

Mentoring Statement

I am committed to supporting my students in achieving their career and life goals, whether that means becoming professors at top universities, research scientists at big tech companies, or making real-world impact in industry or startups. I value ambition and passion, and strive to help students build the competencies needed to meet global standards. Believing in a strong mutual commitment between myself and each student, I plan to keep the lab intentionally small to ensure meaningful collaboration.

Prospective Students: The most important qualities I look for are sincerity toward graduate research and a good fit with the lab. These are best assessed over time, often through internships. If you're interested in joining the lab, please send your CV, transcript, and a short cover letter explaining 1) why you’d like to join and 2) how you can contribute based on your strengths or background. You may submit an SOP instead of the cover letter. I’ll do my best to reply to thoughtful messages, though I may not be able to respond to all.

Members

Co-advising

▪︎ Myeongsoo Kim (co-advised by Prof. Minwoo Chae)

▪︎ Suchan Lee (co-advised by Prof. Hwanjo Yu)

Before Faculty

During my PhD and postdoc, I supported several talented students in successfully completing their first-author projects.

▪︎ Cheng-Lin Hsieh (PhD @ UMich). Mentored during postdoc, working in progress.

▪︎ 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.