About
Representation Analysis & Application Lab. @ Inha University
We study how AI learns meaningful representations from imperfect, structured, and multimodal observations.
Our goal is to develop representation learning principles that enable robust generalization, reliable reasoning, and effective decision making across diverse real-world environments.
Our research combines information-theoretic analysis with modern machine learning to understand how representations emerge, transfer across domains, and support intelligent behavior. Rather than focusing on a single application, we investigate fundamental learning principles that generalize across structured data, multimodal foundation models, and physical AI systems.
Ultimately, we aim to build AI systems that can learn from heterogeneous, incomplete, and continuously evolving real-world information.
Our current research interests include:
- Representation Learning and Generalization
- Information-Theoretic Analysis of Deep Learning
- Structured and Multimodal Foundation Models
- Learning from Imperfect and Heterogeneous Data
- Representation Learning for Physical AI
- Reliable Machine Learning for Real-World Deployment
π Prospective Students
Students interested in joining the lab as undergraduate researchers or MS/Ph.D. students may contact me via email. (νλΆ μ°κ΅¬μ λλ μΒ·λ°μ¬ κ³Όμ μ§νμ κ΄μ¬ μλ νμμ λ©μΌλ‘ μ°λ½ λ°λλλ€.)