Ph.D. student

Graduate School of AI, KAIST

kangyoelk [at] kaist [dot] ac [dot] kr

[Google Scholar][Github][LinkedIn]

I'm a Ph.D. student at Korea Advanced Institute of Science and Technology (KAIST), working on machine learning and its applications under the supervision of Jaegul Choo. My main research interests summarizes as

• Understanding and manipulating visual information such as images and videos
• Learning structure of objects or scenes from images and videos
• Analyzing and detecting of tampered information made by AI

So far, I have researched on generative modeling for predicting, generating and understanding vision dataset. Also, I have an interest in deploying such research for real-world applications.

Publications (C: conference / P: preprint / W: workshop)

[C1] Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation [pdf][site]

• Sunghyun Park*, Kangyeol Kim*, Junsoo Lee, Jaegul Choo, Joonseok Lee, Sookyung Kim, and Edward Choi
• AAAI Conference on Artificial Intelligence (AAAI), 2021 (21% acceptance rate).

[W1] Hurricane Nowcasting with Irregular Time-step using Neural-ODE and Video Prediction [pdf]

• Sunghyun Park*****, Kangyeol Kim*, Sookyung Kim*, Joonseok Lee, Junsoo Lee, Jiwoo Lee, and Jaegul Choo
• International Conference on Learning Representations Workshop (ICLRW), 2020, Accepted as Spotlight Presentation.

[P2] Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE

• Kangyeol Kim*, Sunghyun Park*, Junsoo Lee, Joonseok Lee, Sookyung Kim, Jaegul Choo, and Edward Choi
• Under Review

[P1] Unpaired Image Translation via Adaptive Convolution based Normalization [pdf]