Embedded Files
Research Area
Research Area
LLM & Foundation Model Research
LLM & Foundation Model Research
Mechanistic Interpretability: Understanding what large language models encode internally
Multimodal Understanding: Bridging vision and language for retrieval and comprehension
LLM-powered Reasoning & Applications: Leveraging foundation models for recommendation and structured data understanding
Graph Learning & Recommender Systems
Graph Learning & Recommender Systems
Graph-based Collaborative Filtering: Modeling user-item interactions with variational graph autoencoders for accurate link prediction and recommendation
Long-tail & Robust Recommendation: Addressing popularity bias and distribution shift in graph-based recommenders through decoupled training and re-balancing strategies
LLM-augmented Recommendation: Enhancing recommender systems with large language model reasoning for better generalization and cold-start handling
Secure & Responsible AI
(emerging research direction)
Secure & Responsible AI
(emerging research direction)
LLM Privacy & Security: Investigating membership inference and data extraction attacks against large language models, with a focus on sensitive domains such as healthcare
Machine Unlearning: Enabling models to selectively forget specific training data to satisfy privacy regulations and right-to-be-forgotten requirements
Fairness & Algorithmic Accountability: Auditing and mitigating biases in AI systems, with survey-level analysis of fairness criteria and mitigation strategies across recommendation and classification tasks
On-going Projects
On-going Projects
생성AI선도인재양성사업
Ack: This work was supported by Institute of Information & communications Technology Planning & Evaluation(IITP) under the Leading Generative AI Human Resources Development(IITP-20XX(성과연도)-RS-2026-25544647) grant funded by the Korea government(MSIT)중앙대학교 AI대학원지원사업
Ack: This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [RS-2021-II211341, Artificial Intelligence Graduate School Program (Chung-Ang University)].현대자동차 산학과제 (제조 AI공동연구실)
ITRC - 데이터 안전 활용을 위한 차세대 보안 핵심기술 개발
Ack: This work was supported by the IITP(Institute of Information & Coummunications Technology Planning & Evaluation)-ITRC(Information Technology Research Center) grant funded by the Korea government(Ministry of Science and ICT)(IITP-2026-RS-2024-00438056)
This work was partly supported by the Institute of Information & Communications Technology Planning & Evaluation(IITP)-ITRC(Information Technology Research Center) grant funded by the Korea government(MSIT)(IITP-2026-RS-2024-00438056) and OOO grant funded by the Korea government(OOO)(해당 연구개발과제번호, 기여율)
특허: 【과제고유번호】2710093271중앙대학교 의료 인공지능 특화 융합인재 양성 사업
연구재단 - OTT 사용자 분석을 위한 데이터 결합 및 증식 기술 (외부참여)
Ack: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (RS-2025-00553785).
Past Projects
Past Projects
연구재단 STEAM 과제 - 범국가적 재난 안전관리를 위한 자율·협동지능 대응 원천 기술 개발
Next generation AI for multi-purpose video search (IITP)
Fake News Detection and Content Recommender System (KOCCA)
Development of HW/SW platform for Interactive Self-Monitoring in Real-time Addressing the Mental Health Problems based on Brain-Cognitive Behavioral Data (IITP)
Data Refinement and Improvement through Data Quality Evaluation (IITP)
Reputation Models for Multimodal Social-Log Data (NRF Korea)
Development of emotion recognition/generation-based interacting edge device technology for mental health care (IITP)
Development of an AI Based Video Search System for Untact Content Production (IITP)
Towards XAI on Representation Learning for User Modeling (NRF of Korea)
Report abuse