I am a final-year Ph.D. candidate at KAIST, advised by Jinwoo Shin. I also work closely with Saining Xie at NYU. During my Ph.D., I interned at Google Research/DeepMind and NVIDIA Research to design efficient video generation models. I also collaborated with Kihyuk Sohn through the university relations program at Google Research.
I am broadly interested in a range of problems in computer vision. In particular, my research focuses on the intersection of visual representation learning and generative modeling towards unified, human-like vision models capable of both creating and understanding complex visual worlds. I am also interested in AI4Science and have contributed to several related projects.
Apr 2025: I received Google Conference Scholarships (APAC). Apr 2025: I am attending ICLR in person. See you in Singapore! Mar 2025: I gave a talk at Sheffield NLP. Feb 2025: BootComp and CoordTok are accepted to CVPR 2025. Jan 2025: REPA is accepted to ICLR 2025 as an oral presentation! Oct 2024: I gave a talk at BioImaging, Signal Processing & Learning Lab at KAIST. Jun 2024: I am attending CVPR in person. Looking forward to seeing you in Seattle! May 2024: I am attending ICLR in person. See you in Vienna! May 2024: Hi-Mol is accepted to ICML 2024. |
|
Google Research
NVIDIA Research
Google Research |
Recipient, ICLR 2025 Google Conference Scholarships (APAC)
|
Training Diffusion Transformers Is Easier Than You Think
Efficient Latent Video Diffusion Models via Triplane Encoding
Video Probabilistic Diffusion Models in Projected Latent Space
Efficient Generative Models for Videos
RoMA: Robust Model Adaptation for Offline Model-based Optimization
Scaling Video Generation via Implicit Neural Representations
Abstract Reasoning via Logic-guided Generation |
Conference reviewer: ICML'22-25, NeurIPS'22-25, ICLR'23-25, CVPR'23-25, ICCV'23-25, ECCV'24, WACV'25, AAAI'25, AISTATS'25
|
Teaching Assistant, Deep Learning, Fall 2020
|