I’m Youngwan, a senior researcher at ETRI and Ph.D student in Graduate school of AI at KAIST, where I’m advised by Prof. Sung Ju Hwang in the Machine Learning and Artificial Intelligence (MLAI) lab. My research interest is how computers understand the world, including efficient 2D/3D neural network design, object detection, instance segmentation, semantic segmentation, and video classification 🖥️🌏. Recently, I have focused on Vision Transformer architecture and self-supervised learning.

🎉 News

  • 2024.09:  🎉🎉 KOALA has been accepted at NeurIPS 2024.
  • 2024.08:  🎉🎉 DiT-Pruner has been accepted at ECCVW 2024.
  • 2024.05:  🎉🎉 EVEREST has been accepted at ICML 2024.
  • 2023.12:  🎉🎉 KOALA, a fast Text-to-Image sythesis model, has been released.
  • 2023.02:  🎉🎉 Two papers have been accepted at ICLR 2023.
  • 2022.02:  🎉🎉 One paper has been accepted at CVPR 2022.

📚 Publications

Google Scholar full list

  • KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

    Youngwan Lee, Kwanyong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang
    Advances in Neural Information Processing Systems (NeurIPS) 2024
    CVPR 2024 Workshop on Generative Models for Computer Vision
    [Project page][paper][code]

  • DiT-Pruner: Pruning Diffusion Transformer Models for Text-to-Image Synthesis Using Human Preference Scores

    Youngwan Lee, Yong-Ju Lee, Sung Ju Hwang
    European Conference on Computer Vision (ECCV) 2024 Workshop on Green Foundation Models
    [paper]

  • PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation

    Injoon Hwang, Haewon Park, Youngwan Lee*, Jooyoung Yang, SunJae Maeng
    *:equal contribtion
    Computer Vision and Pattern Recognition (CVPR) 2024 Workshop on Transformers for Vision (T4V), Spotlight
    [paper]

  • EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

    Sunil Hwang*, Jaehong Yoon* Youngwan Lee*, Sung Ju Hwang
    *:equal contribtion
    Internation Conference on Machine Learning (ICML) 2024
    CVPR 2024 Workshop on Transformers for Vision (T4V), Spotlight
    [paper]

  • Visualizing the loss landscape of Self-supervised Vision Transformer

    Youngwan Lee, Jeffrey Ryan Willette, Jonghee Kim, Sung Ju Hwang
    Conference on Neural Information Processing Systems (NeurIPS) 2023 Workshop on Self-Supervised Learning - Theory and Practice
    [paper]

  • Exploring the Role of Mean Teachers in Self-supervised Masked Auto-Encoders

    Youngwan Lee*, Jeffrey Ryan Willette*, Jonghee Kim, Juho Lee, Sung Ju Hwang
    *:equal contribtion
    Internation Conference on Learning Representation (ICLR) 2023
    [paper][poster][slide]|

  • Sparse Token Transformer with Attention Back Tracking

    Heejun Lee, Minki Kang, Youngwan Lee, Sung Ju Hwang
    Internation Conference on Learning Representation (ICLR) 2023
    [paper][poster][slide]

  • MPViT: Multi-Path Vision Transformer for Dense Prediction

    Youngwan Lee, Jonghee Kim, Jeffrey Ryan Willette, Sung Ju Hwang
    Computer Vision and Pattern Recognition (CVPR) 2022
    [paper][poster] [slide]|

  • Localization Uncertainty Estimation for Anchor-Free Object Detection

    Youngwan Lee, Joong-Won Hwang, Hyung-Il Kim, Kimin Yun, YongJin Kwon, Yuseok Bae, Sung Ju Hwang
    European Conference on Computer Vision Workshop on Uncertainty Quantification for Computer Vision (ECCVW) 2022
    [paper][poster][slide]

  • Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification

    Youngwan Lee, Hyung-Il Kim, Kimin Yun, Jinyoung Moon
    IEEE Access 2021
    [paper] |

  • Adversarial training with stochastic weight average

    Joong-Won Hwang, Youngwan Lee, Seongchan Oh, Yuseok Bae
    International Conference on Image Processing (ICIP) 2021
    [paper]

  • Anti-Litter Surveillance based on Person Understanding via Multi-Task Learning

    Kangmin Bae, Kimin Yun, Hyung-Il Kim, Youngwan Lee, Jongyoul Park
    The British Machine Vision Conference (BMVC) 2020
    [paper]

  • CenterMask: Real-Time Anchor-Free Instance Segmentation

    Youngwan Lee, Jongyoul Park
    Computer Vision and Pattern Recognition (CVPR) 2020
    [paper] |

  • An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection

    Youngwan Lee*, Joong-Won Hwang*, Sangrok Lee, Yuseok Bae, Jongyoul Park
    *:equal contribtion
    Computer Vision and Pattern Recognition Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision (CVPRW) 2019
    [paper][timm]|

🎖 Honors and Awards

  • 2024.04 Best Paper Award, ETRI
  • 2022.12 Ministerial Citation (장관표창), Minister of Science and ICT, South Korea
  • 2022.04 Best Lecturer Award, ETRI
  • 2022.04 Best Paper Award, ETRI
  • 2017.06 2nd rank in ImageNet Challenge (Detection task, Team DeepView)

💻 Academic Services

  • Lecturer
    • 2020-present, AI Academy at ETRI
    • 2022-2023, Hallym University Medical Center
    • 2022, Korea Atomic Energy Research Institute
  • Reviewer
    • Journal
      • IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
      • IEEE Transactions on Image Processing (T-IP)
      • IEEE Transactions on Intelligent Transportation Systems (T-ITS)
      • IEEE Transactions on Vehicular Technology (T-VT)
      • IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT)
      • International Journal on Computer Vision (IJCV)
    • Conference
      • CVPR 2023 2024
      • NeurIPS 2023 2024
      • ICML 2023 2024
      • ICLR 2024 2025
      • ICCV 2023
      • ECCV 2024
      • AAAI 2025