Sangwoo Mo

Assistant Professor

POSTECH IME, affiliated with IDS

Email: {first_name}.{last_name} [at] postech.ac.kr

Office: Engineering Building 4, Room 319

Tel: +82-54-279-2202

Google Scholar / Github / CV / Twitter

I will be recruiting students for Spring 2026. Feel free to reach out!

I am an assistant professor at POSTECH in the Department of Industrial and Management Engineering (IME), affiliated with the Graduate School of Industrial Data Science (IDS). Previously, I was a postdoctoral fellow at the University of Michigan, working with Prof. Stella X. Yu, and earned my Ph.D. from KAIST under the supervision of Prof. Jinwoo Shin. I have collaborated with leading research labs including Google, Meta, NVIDIA, Naver, and Kakao, and have been supported by fellowships from Samsung, Qualcomm, and the Korean AI Association.

My research goal is to design scalable priors for AI. Even in the era of data-centric foundation models, I believe that well-designed priors can enhance performance, reliability, and interpretability. My previous work has shown that incorporating inductive biases, such as scene structures and data uncertainties, enables models to tackle more complex and diverse tasks. These efforts span perception, generation, and action across domains including vision, language, and robotics. In summary, my research includes:

1. Structural Priors for Effective Learning

Encode domain-specific structures to improve performance and interpretability

- Vision (perception): OACon (NeurIPS'21), OAMixer (CVPRW'22), CAST (ICLR'24), OAK (CVPR'25)

- Vision (generation): InstaGAN (ICLR'19), DIGAN (ICLR'22), SHED (arXiv'25)

- Language: HOMER (ICLR'24), SuRe (ICLR'24), Simba (TMLR'25)

- Robotics: EIT-NN (IROS'19), EIT-NN-v2 (T-RO'21)

- Logic & graph: LoGe (ICMLW'21), DPM-SNC (NeurIPS'23)

2. Statistical Priors for Reliable Learning

Estimate and leverage dataset statistics to improve robustness and generalization

- Perception: CSI (NeurIPS'20), MASKER (AAAI'21), RoPAWS (ICLR'23), S-CLIP (NeurIPS'23)

- Generation: GOLD (NeurIPS'19), FreezeD (CVPRW'20), FICS (TMLR'23)

- Trustworthy: B2T (CVPR'24)

- Architecture: LAP (ICLR'20), LAMP (ICLR'21)

A full publication list and mentoring experience can be found here.

News

▪︎ 2025/10: Will serve as an organizer for the SP4V (structural priors for vision) Workshop @ ICCV'25.

▪︎ 2025/09: Will start as an assistant professor at POSTECH! 🧑‍🏫

▪︎ 2025/06: Served as an organizer for the PixFoundation (pixel-level vision foundation) Workshop @ CVPR'25.

▪︎ 2025/05: Selected as a notable reviewer for ICLR'25.

▪︎ 2025/02: Paper on category discovery accepted at CVPR'25.

▪︎ 2025/02: Paper on state-space model accepted at TMLR'25.

▪︎ 2024/06: Served as a committee for the POETS (virtual humans for robotics) Workshop @ CVPR'24.

▪︎ 2024/02: Paper on language for vision (highlight) accepted at CVPR'24.

▪︎ 2024/01: Papers on visual representation (spotlight), LLM long context, and LLM reasoning accepted at ICLR'24.

▪︎ 2023/09: Papers on vision-language model and structured prediction accepted at NeurIPS'23.

▪︎ 2023/09: Started a postdoctoral fellowship at the University of Michigan.

▪︎ 2023/06: Successfully defended my PhD thesis! 🧑‍🎓

Appointments

Faculty positions

▪︎ POSTECH, Assistant Professor / 2025–current (Korea)

Research positions

▪︎ U Michigan, Postdoctoral Fellow (host: Prof. Stella X. Yu) / 2023–2025 (US)

▪︎ NVIDIA AI, Research Intern (host: Dr. Weili Nie) / 2022 Winter (US, remote)

▪︎ Meta AI, Research Intern (host: Dr. Jong-Chyi Su) / 2022 Summer (US)

▪︎ Naver AI, Collaborator (host: Dr. Jung-Woo Ha) / 2021 Summer (Korea)

▪︎ Google AI, Collaborator (host: Dr. Kihyuk Sohn) / 2020 Winter (US, remote)

▪︎ Kakao Brain, Research Intern (host: Dr. Sungwoong Kim) / 2019 Spring (Korea)

Education

▪︎ KAIST, M.S./Ph.D. in Electrical Engineering, 2023 (advisor: Prof. Jinwoo Shin)

- Ph.D. Thesis: Learning Visual Representations from Uncurated Data

▪︎ POSTECH, B.S. in Mathematics & Industrial Engineering (minor), 2016 - summa cum laude

Services

▪︎ Workshop Committee:

- Structural Priors for Vision (SP4V) @ ICCV'25

- Pixel-level Vision Foundation Models (PixFoundation) @ CVPR'25

- Virtual Humans for Robotics and Autonomous Driving (POETS) @ CVPR'24

▪︎ Conference Reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, COLM, AAAI, AISTATS

▪︎ Journal Reviewer: TPAMI, TMLR, TNNLS, IJCV, ML, and others