IDEA Lab @ Korea Univ.

Welcome to Intelligent Data Science and Applications Lab 😀

In today's world, we are experiencing an explosion of information. Every day, over 2 million blog posts, more than a thousand academic papers, and 3 million Youtube videos are uploaded. With this increasing volume of information, we often face challenges in finding the optimal information, whether it’s deciding what to eat, what to wear, or which papers to read. Simply says, we are overwhelmed by vast amounts of information.

Our mission is to develop intelligent systems that empower individuals to navigate this overwhelming sea of information effectively. We aim to deliver relevant, high-quality, and actionable insights tailored to each user's unique context and needs.

 Research Areas (Details) 

We work on a wide range of topics related to data science, AI, and LLMs. Our current interests include, but are not limited to, the following areas:

• Retrieval-Augmented Generation (RAG): Designing retrieval and knowledge grounding strategies to enhance LLM generation. 

• Recommendation & Personalization: Modeling user preferences, and long-term interests for personalized ranking and recommendation.

• Search in Specialized Domains: Retrieval for domain-specific corpora (e.g., scientific literature, e-commerce, enterprise data). 

• Multi-modal and Multi-domain Generalization: Integrating text, image, graph, and other modalities for retrieval and recommendation.

• Continual Retrieval and Recommendation: Handling evolving data distributions, user interest drift, and non-stationary environments. 

• Efficient and Scalable Systems: Lightweight models, indexing strategies, and efficiency–effectiveness trade-offs for resource-constrained settings. 

 Recent News 

2026

• Accepted paper: "SPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-based Recommendation", SIGIR, 2026

• Accepted paper: "Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders", SIGIR, 2026

• Accepted paper: "FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation", SIGIR, 2026

• Accepted paper: "MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender", SIGIR, 2026

• Invited talk: "Knowledge-Structured Retrieval for Scientific Literature", CSE/GSAI Seminar, POSTECH, 2026

• Accepted paper: "Continual Low-Rank Adapters for LLM-based Generative Recommender Systems", ICLR, 2026

• Accepted tutorial: "Continual Recommender Systems", DASFAA, 2026

• Accepted paper: "Capturing User Interests from Data Streams for Continual Sequential Recommendation", WSDM, 2026

• Accepted paper: "PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval", WWW, 2026

• Accepted paper: "CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory", KDD, 2026

• Accepted paper: "BPL: Bias-adaptive Preference Distillation Learning for Recommender System", TKDE, 2026

• Professional service: Prof. Kang has been invited to be an Area Chair of KDD, and a PC member of SIGIR