Multi-Modal Artificial Intelligence Lab
Multi-modal AI research connecting vision, language, and diverse signals for real-world impact.
- Computer Vision
- Efficient LLMs
- Robot Learning
Laboratories
AAIG brings together five research labs working across vision, speech, embodied intelligence, and knowledge-based AI.
SAIL
Sanghoon Lee이상훈Speech Artificial Intelligence Lab
Research on speech synthesis, speech language models, and generative models for audio, talking-head, and video generation.
- Speech Synthesis
- Speech Language Models
- Generative Models
Human-Centered Embodied Intelligence Lab
Building robots that learn, adapt, and interact with people through foundation models for robotics, human-robot interaction, and lifelong learning.
- Robot Learning
- Human-Robot Interaction
- Lifelong Learning
intelligence and Knowledge Lab
Research on recommendation systems, multimodal understanding, large language models, and federated learning.
- Recommendation
- Multimodal AI
- Large Language Models
LAMDA Lab
Kyung-Ah Sohn손경아Learning and Mining from DAta Lab
Multimodal, self-supervised, explainable, and trustworthy AI for biomedical, social, and other real-world data.
- Multimodal Learning
- Trustworthy AI
- Biomedical AI
Student Representatives
MMAI Lab
Donggeon Lee이동건
Ph.D. Student and student representative
donggeon_lee@ajou.ac.krSAIL
Student representative추후 안내
To be announced
HEI Lab
Student representative추후 안내
To be announced
iKnow Lab
Student representative추후 안내
To be announced
LAMDA Lab
Student representative추후 안내
To be announced