Wongi Jeong

MS / Ph.D student ICL @ ECE, SNU

Introduce

I am a fifth-year MS/Ph.D student in electrical and computer engineering (ECE) at Seoul National University (SNU), advised by Prof. Se Young Chun. I earned my B.S degree in electrical and computer engineering (ECE) from Seoul National University (SNU).

Research Interests

My research interests lie in \textbf{efficient generative AI}: making generative models resource-, computation-, and parameter-efficient across every stage of development and deployment, and validating these efficiency claims on real, constrained hardware rather than relying on algorithmic metrics alone. While I am interested in both Natural Language Processing (NLP) and Computer Vision (CV), my current focus is on generative vision models, particularly diffusion-based image and video generation. Specifically, my research explores, but is not limited to, the following areas:

  • Efficient Deep Learning
  • Hardware-aware Model Compression
  • On-device Learning and Adaptation

Researches

2026
CVPR26 Thumbnail

Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers [arXiv] [project] [code]

CVPR 2026 (Highlight)

Wongi Jeong*, Kyungryeol Lee*, Hoigi Seo, Se Young Chun (*co-first)

Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models [arXiv] [project]

CVPR 2026

Wongi Jeong*, Hoigi Seo*, Se Young Chun (*co-first)

2025
ICCV25 Thumbnail

Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis [arXiv] [project] [code]

ICCV 2025

Byung Hyun Lee, Wongi Jeong, Woojae Han, Kyoungbun Lee, Se Young Chun

ICML25 Thumbnail

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation [arXiv] [project]

ICML 2025

Hoigi Seo*, Wongi Jeong*, Jae-sun Seo, Se Young Chun (*co-first)

CVPR25 Thumbnail

Efficient Personalization of Quantized Diffusion Model without Backpropagation [paper] [arXiv] [project] [code]

CVPR 2025 / CVPRW (EDGE) 2025

Hoigi Seo*, Wongi Jeong*, Kyungryeol Lee, Se Young Chun (*co-first)

ISMRM25 Thumbnail

Harmonization for a black-box deep learning model

ISMRM 2025 (Oral, Summa cum laude)

Minjun Kim, Hwihun Jeong, Hoigi Seo, Wongi Jeong, Juhyung Park, Se Young Chun, Jongho Lee

2023
ICCV23 Thumbnail

Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors [paper] [arXiv] [project] [code]

ICCV 2023

Haechang Lee*, Dongwon Park*, Wongi Jeong*, Kijeong Kim, Hyunwoo Je, Dongil Ryu, Se Young Chun (*co-first)

ICCVW23 Thumbnail

Fully Quantized Always-on Face Detector Considering Mobile Image Sensors [arXiv]

ICCVW 2023 (Oral)

Haechang Lee*, Wongi Jeong*, Dongil Ryu*, Hyunwoo Je, Albert No, Kijeong Kim**, Se Young Chun** (*co-first, **co-corresponding)

Recent posts