Data & Adaptive Intelligence Systems Lab
Korea University
Mission
Empower innovation through data-driven insights, fostering intelligence systems with adaptive capabilities
Image created by DALL·E
We are currently seeking undergraduate researchers starting in January 2025 [Official post (Korean)]
📰 News
2024.10 Â
Susik gave talks at AI Tech Day and Kongju National University
A paper on continual network coreness prediction (in collaboration with UNIST) received the best paper award (silver prize) at KDBC 2024
2024.09 Â
A paper on time series segmentation accepted to NeurIPS 2024
2024.08 Â
We started the Global Basic Research Laboratory project on compound disaster prediction with multi-modal AI (funded by National Research Foundation of Korea, in collaboration with Kongju National University and the University at Buffalo)
We started the project on a foundation model for structured data with KT
2024.07Â
Twelve undergraduate students, one researcher, and one master student joined DAIS Lab
A paper on the clique problem accepted to CIKM 2024
2024.06
Susik gave a talk at CHA Medical School and Korea Computer Congress 2024
We presented two undergraduate poster papers (with one best paper award) at Korea Computer Congress 2024
2024.05
A paper on online concept drift detection accepted to KDD 2024Â
Susik had an interview with the ICT Creative Consilience Program at Korea University (Link(Korean))
A paper on adaptive prompt tuning for continual learning accepted to ICML 2024Â
2024.04Â
Two undergraduate students joined DAIS LabÂ
2024.03
DAIS Lab at Korea University opened 🎉
📋Research Area
We are interested in broad topics in Data Science (DS) and Artificial Intelligence (AI). We identify real-world challenges with significant practical impacts and address them through DS/AI methodologies by leveraging {Evolving, (Un)structured data} X {Foundation models} X {Human-curated knowledge}.
Examples of research topics include, but are not limited to,
DS and AI methodologies
Data mining, Machine learning, Deep learning, Multi-modal learning
Anomaly detection, Classification, Clustering, Recommendation, Summarization
Learning from evolving data
Real-time machine learning, Continual learning, Data stream mining, Time-series mining, Concept drift adaptation
Learning from (un)structured data
Natural Language Processing, Text mining, Information retrieval, Knowledge structuration, Representation learning
Exploiting Foundation models (i.e., pretrained language, vision, multimodal models)
Retrieval-augmented generation, Prompt tuning, Model adaptation
Exploiting human-curated knowledge (i.e., Knowledge base, metadata, weak labels)
Semi/weakly-supervised learning, Active learning, Knowledge base, Fake detection
See our [publications]