Sangheum Hwang
Scholar

Sangheum Hwang

Google Scholar ID: QtI8XmgAAAAJ
Seoul National University of Science and Technology
Machine LearningDeep LearningArtificial IntelligenceStatistical Data Mining
Citations & Impact
All-time
Citations
2,318
 
H-index
16
 
i10-index
21
 
Publications
20
 
Co-authors
21
list available
Contact
No contact links provided.
Resume (English only)
Academic Achievements
  • Publications:
  • - [CVPR 2025] Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
  • - [CVPR 2025] APT: Adaptive Personalized Training for Diffusion Models with Limited Data
  • - [ICLR 2025] Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
  • - [AAI] Metadata Enriched Multi-Instance Contrastive Learning for High-Quality Facial Skin Visual Representations
Research Experience
  • Research Projects: Application and safety enhancement of foundation models (such as large language models and multimodal models); Specific research areas include: unlearning techniques, safety alignment, concept erasing, and personalization techniques.
Background
  • Research Interests: Data mining and machine learning algorithms; Professional Field: Analysis of image, text, and time-series data; Summary: Focuses on designing intelligent systems based on learning patterns or rules from large-scale data, with applications in manufacturing, service, and healthcare industries.
Miscellany
  • Looking for passionate students interested in machine learning and deep learning to join the lab.