- ETRI & MLAI@KAIST
- South Korea
- 03:02
(UTC +09:00) - https://youngwanlee.github.io/
- in/youngwanlee
Highlights
- Pro
👋 Hi there! I'mYoungwan, asenior researcher atETRI andPh.D student in Graduate school of AI atKAIST, where I'm advised by Prof.Sung Ju Hwang in theMachine 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 🖥️🌏. Besides, I have explored Vision Transformer architecture and self-supervised learning.Recently, I have focused on multimodal learning, including text-image generation and safety for vision-language models.
SeeGoogle scholar for full list.
- KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis,NeurIPS 2024.
- RC-MAE: Exploring the Role of Mean Teachers in Self-supervised Masked Auto-Encoders,ICLR 2023.
- MPViT : Multi-Path Vision Transformer for Dense Prediction,CVPR 2022.
- CenterMask : Real-Time Anchor-Free Instance Segmentation,CVPR 2020.
- VoV3D: 3D convolutional neural network,IEEE Access 2021.
- VoVNet: 2D convolutional neural network,CVPRW 2019.
- 📝 I enjoy
teachingtalking what Iknowlearn, so I am giving lectures on AI as an AI Facilitator at ETRI AI Academy. - 🌏🌱🌲🌊 ⛰️ I love to appreciate the beautiful nature.
- 🎾 🏀 I enjoy playing tennis and basketball.
- 📫 How to reach me:yw.lee@etri.re.kr |ywlee88@kaist.ac.kr
PinnedLoading
- sdxl-koala
sdxl-koala Public[NeurIPS 2024] Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
- centermask2
centermask2 Public[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation
- vovnet-detectron2
vovnet-detectron2 Public[CVPR 2020] VoVNet backbone networks for detectron2
- CenterMask
CenterMask Public[CVPR 2020] CenterMask : Real-Time Anchor-Free Instance Segmentation
If the problem persists, check theGitHub status page orcontact support.
Uh oh!
There was an error while loading.Please reload this page.