Welcome to DUCK Lab!
- 2026.07 - Our project has been selected for the AI 연구용 컴퓨팅 지원 프로젝트.
- 2026.05 - A paper has been accepted to a top-tier conference, ICML. View article
- 2026.04 - Our lab has secured the 지능형 금지약물 관리를 위한 플랫폼 기술 개발 with Professor Sunoh Kim serving as the PI. View article
- 2026.02 - A paper has been accepted to a top-tier conference, CVPR. View article
- 2026.01 - Two papers have received Honorable Mention awards at KSC.
- 2025.12 - Our project has been selected as the Best Project in 고성능 컴퓨팅 지원사업.
- 2025.11 - A paper has been accepted to a top-tier journal, IEEE TMM. View article
- 2025.05 - A paper has been accepted to a top-tier conference, ICML.
- 2025.03 - Professor Sunoh Kim has joined the faculty at Dankook University.
- 2025.01 - A paper has been accepted to a top-tier conference, ICLR.
Research
Multimodal AI
Developing AI systems that align, ground, and reason across images, videos, text, and actions for a richer understanding of complex environments
Trustworthy AI
Improving the reliability of AI under distribution shifts, adversarial attacks, and hallucinations through robustness analysis, mitigation, and rigorous evaluation
Adaptive AI
Enhancing AI models during inference through adaptation and optimization to improve generalization across changing tasks, data distributions, and environments
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
ICML 2026
When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness
CVPR 2026
Finding Optimal Video Moment without Training: Gaussian Boundary Optimization for Weakly Supervised Video Grounding
IEEE Transactions on Multimedia 2026
Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
ICML 2025
Spreading Out-of-Distribution Detection on Graphs
ICLR 2025
Learnable Negative Proposals Using Dual-Signed Cross-Entropy Loss for Weakly Supervised Video Moment Localization
MM 2024
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
AAAI 2024
Gallery
Apply
Recruitment
We are looking for motivated graduate students and undergraduate research interns to join our lab. If you are interested, please submit your academic transcript and CV to the email address below.
저희 연구실에서는 열정적인 대학원생과 학부 연구 인턴을 모집하고 있습니다. 관심 있는 분들은 아래 이메일로 성적증명서와 CV(이력서)를 보내주세요!
suno8386@dankook.ac.kr