Publications: ICLR'22 'Multi-Task Processes', ICLR'21 'Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction', AAAI'21 'IB-GAN: Disentangled Representation Learning with Information Bottleneck GAN', ECCV'20 'High-Fidelity Synthesis with Disentangled Representation'.
Research Experience
Worked as an AI research scientist at ART Lab, leading a project for digitizing and interpreting human faces by solving multi-task learning problems, including 3D reconstruction, semantic segmentation, object detection, landmark detection, pose estimation, and attributes regression. Contributed to a patent application related to automatic photography using electronic devices.
Education
PhD student at Seoul National University, advised by Prof. Gunhee Kim; MSc from the School of Computing at KAIST, supervised by Prof. Seunghoon Hong; B.S. in Electrical and Electronic Engineering from Hanyang University (HYU).
Background
Research interests lie in machine learning and computer vision, particularly in generative modeling and representation learning. Worked on a video prediction project at Google Brain, showing unprecedentedly high-quality and long-term video predictions through hierarchical generative models.