About Me

Hi! 👋 I am a second-year MS/PhD integrated student in Electrical and Computer Engineering at Seoul National University. Under the supervision of Professor Se Young Chun, my research interests include, but are not limited to:

• Efficient AI: acceleration, pruning, quantization, etc.
• Safety AI: watermark, machine unlearning, etc.

Email: kr.lee@snu.ac.kr

Research

2026

• Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers

  Wongi Jeong*, Kyungryeol Lee*, Hoigi Seo, Se Young Chun (*co-first)
  Accepted at Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (Highlight)

  [arXiv] [project] [code]

• Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models

  Kyungryeol Lee*, Kyeonghyun Lee*, Seongmin Hong*, Byung Hyun Lee, Se Young Chun (*co-first)
  Accepted at CVPR Workshop on Machine Unlearning for Vision, 2026.

  [arXiv]

2025

• Efficient Personalization of Quantized Diffusion Model without Backpropagation

  Hoigi Seo*, Wongi Jeong*, Kyungryeol Lee, Se Young Chun (*co-first)
  Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

  [Paper] [supp] [arXiv] [project] [code]

• Robust Watermarks for Audio Diffusion Models by Quadrature Amplitude Modulation

  Kyungryeol Lee*, Seongmin Hong*, Se Young Chun (*co-first)
  Pattern Recognition Letters, 2025.

  [Paper]