Multimodal Orchestration of
Artificial Intelligence Lab
We orchestrate foundation models across vision, language, and physical sensors to drive AI agents, robots, and automated factories.
Our focus in 2026
VAP · ICML'26
Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting
INDI · arXiv'26
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
PeopleGyeom HwangboWon-Sik Oh
I2A · WACV'27
Instruct2Alert: Decoupling Visual Verification from Temporal Alert Control in Video Safety Monitoring
PRISM · arXiv'26
PRISM: Interpreting Time-series Foundation Models via Zero-shot Basis Decoding
Our work appears at top AI conferences such as
NeurIPS, ICML, and ICLR. See our publications →
We're actively recruiting students and interns with a passion for AI and AX. Join us! 🚀
News
- Paper on safety monitoring (application) accepted at WACV'27.
- Paper on dense prediction accepted at TMLR'26.
- Papers on fair diffusion, VLM learning, and visual grounding accepted at NeurIPS'26.
- Served as an Area Chair for ICLR'27.
- Paper on VLM reasoning (oral) accepted at EMNLP'26.
- Paper on personal robots accepted at ICML'26.
- Paper on test-time scaling accepted at CVPR'26.
- Paper on dataset distillation accepted at ICLR'26.
- Organized the SP4V (structural priors for vision) workshop at ICCV'25.
- MOAI Lab started at POSTECH.