-
I am currently working on controllable image and video generative models.
-
I am currently affilitated in SNU CSE and Adobe Research.
-
I am interested in, but not limited to: generative models, multi-modal / video understanding.
-
For more details, visit my homepage.
-
I am open to discuss, collaborate on topics above. Feel free to reach out!
Highlights
- Pro
Pinned Loading
-
SNU-VGILab/improving-editability
SNU-VGILab/improving-editability Public[Official Implementation] Improving Editability in Image Generation with Layer-wise Memory, CVPR 2025
-
disentangled-subject-to-vid
disentangled-subject-to-vid PublicLearning Zero-Shot Subject-Driven Video Generation Using 1% Compute
Python 59
-
RCEdit-500K
RCEdit-500K Public[ECCV 2026] RCEdit-500K: Reference Completion for Image-Conditioned Image Editing
Python
-
PiX
PiX PublicForked from ashishkumar822/PiX
PiX: Dynamic Channel Sampling for ConvNets (CVPR 2024)
Python 1
-
cmota
cmota PublicForked from yonseivnl/cmota
Story Visualization by Online Text Augmentation with Context Memory, ICCV'23
Python 1
If the problem persists, check the GitHub status page or contact support.



