About Me

I am a Ph.D. student at SKKU (Sungkyunkwan University), South Korea, advised by Prof. Sungeun Hong in the AI & Media Lab (AIM Lab). My research interests include vision-language models, multimodal learning, visual token pruning, and test-time adaptation.

🔥 News

• 2026.02:  🎉🎉 One paper is accepted to CVPR 2026.
• 2025.09:  🎉🎉 One paper is accepted to NeurIPS 2025.
• 2025.06:  🎉🎉 One paper is accepted to IJCV 2025 (Q1, JCR: Top 10%).

📝 Publications

^* Equal contribution. ^† Corresponding author.

• ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models
  • Youngeun Kim^*, Youjia Zhang^*, Huiling Liu, Aecheon Jung, Sunwoo Lee, and Sungeun Hong^†
  • CVPR 2026 [Project page]
• Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
  • Youjia Zhang, Youngeun Kim, Young-Geun Choi, Hongyeob Kim, Huiling Liu, and Sungeun Hong^†
  • NeurIPS 2025 [Project page]
• CAT-TPT: Class-Agnostic Text-based Test-time Prompt Tuning for Vision-Language Models
  • Youjia Zhang, Huiling Liu, Youngeun Kim, and Sungeun Hong^†
  • IJCV 2025 [Q1, JCR Top 3%, IF 11.6] [DOI]

📁 Projects

• Visuo-Tactile World Model for Dexterous Robotic Manipulation with Non-Standard Sensors (2026.03 – Present)

  • Funded by the National Research Foundation of Korea
  • This project studies a world model-based robotic manipulation framework that integrates visual and tactile information under non-standard tactile sensor environments. It focuses on sensor-invariant tactile representation learning and visuo-tactile sim-to-real transfer for stable and precise robotic manipulation across diverse sensors and environments.

• Human-oriented AI Model that Imitates the Human Growth Process based on Cognitive Science (2025.04 – 2025.12)

  • Funded by the Institute for Information & Communications Technology Promotion (IITP)
  • This project aims to develop a human-oriented AI model that can understand and explain diverse physical phenomena and causal relationships through cognitive science-inspired learning mechanisms.

🎖️ Honors and Awards

• SKKU STEM Full Scholarship, 2024 – Present.
• IEIE Encouraging Paper Award, 2024.

🪄 Patents

• Apparatus and Method for Prompt Tuning ( U.S. Patent Application No. 19/545,275; Pending.)

💬 Academic Activities

• Reviewer

  • NeurIPS 2025
  • CVPR 2026

• Teaching Assistant

  • Advanced Machine Learning / Deep Learning, SKKU, Spring 2026.
  • Generative Deep Learning, SKKU, Fall 2025.
  • Introduction to Deep Learning, SKKU, Spring 2025.
  • Introduction to Deep Learning, SKKU, Fall 2024.

🎓 Education

• Sungkyunkwan University, South Korea, 2024.03 - Present
  • Ph.D. Student, Department of Immersive Media Engineering
  • Advisor: Prof. Sungeun Hong
• Chongqing University of Technology, China, 2020.09 - 2023.06
  • M.S. in Information and Communication Engineering
  • Advisor: Prof. Nan Xiang
• KAIST, South Korea, 2022.03 - 2022.08
  • Visiting Student, NICA Lab
• Suzhou University, China, 2015.09 - 2019.06
  • B.Eng. in Communication Engineering