profile photo

Sihyun Yu

sihyun.yu at kaist dot ac dot kr
yusihyunc at gmail dot com


I am a Ph.D. student at KAIST, advised by Jinwoo Shin. I also work closely with Kihyuk Sohn, who is at Google Research. Prior to this, I received B.S. in Computer Science and Mathematics (double major) at KAIST under the supervision of Hongseok Yang and Juho Kim, who kindly advised me to be a conscientious researcher.

Currently, I am a research intern at NVIDIA Research, working with wonderful mentors Weili Nie, Zhiding Yu, De-An Huang, Boyi Li, and Anima Anandkumar.


Mar 2023: I am joining NVIDIA Research as a research intern.
Mar 2023: ECoP is accepted to ICLR 2023 Workshop on Neural Fields across Fields.
Feb 2023: Two papers (PVDM and AENIB) are accepted to CVPR 2023.
Nov 2022: I will attend NeurIPS 2022 offline.
Sep 2022: NVP is accepted to NeurIPS 2022.


My research lies in making deep generative models scalable towards real-world high-dimensional data and their deployment to real-world scenarios. To achieve this goal, I usually focus on alleviating huge memory burdens or computations of deep generative models. Currently, I am mainly working in video synthesis, but not limited to; other complex data (e.g., 3D scenes and graphs), and any other applications are also in my broad interest. Besides, I also have an interest in the robustness of neural networks to the distributional shift.

Learning Large-scale Neural Fields via Context Pruned Meta-Learning
Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin, Jonathan Richard Schwarz
ICLR 2023 Workshop on Neural Fields across Fields.
paper  |  code

Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
Jongheon Jeong, Sihyun Yu, Hankook Lee, Jinwoo Shin
CVPR 2023
paper  |  code

Video Probabilistic Diffusion Models in Projected Latent Space
Sihyun Yu, Kihyuk Sohn, Subin Kim, Jinwoo Shin
CVPR 2023
paper  |  project page  |  code

Scalable Neural Video Representations with Learnable Positional Features
Subin Kim*, Sihyun Yu*, Jaeho Lee, Jinwoo Shin
NeurIPS 2022
paper  |  project page  |  code

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Sihyun Yu*, Jihoon Tack*, Sangwoo Mo*, Hyunsu Kim, Junho Kim, Jung-Woo Ha, Jinwoo Shin
ICLR 2022
paper  |  project page  |  slide  |  code

Consistency Regularization for Adversarial Robustness
Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, Jinwoo Shin
AAAI 2022
paper  |  slide  |  code

RoMA: Robust Model Adaptation for Offline Model-based Optimization
Sihyun Yu, Sungsoo Ahn, Le Song, Jinwoo Shin
NeurIPS 2021
paper  |  slide  |  code

Abstract Reasoning via Logic-guided Generation
Sihyun Yu, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception   (oral)
paper  |  slide  |  poster

Work Experience

NVIDIA Research
Research Intern, hosted by Weili Nie (Mar 2023 - present)

Google Research
Google University Relations, hosted by Kihyuk Sohn (Jul 2022 - present)

External Collaborator, hosted by Jung-Woo Ha (Jun 2021 - Sep 2021)

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
External Collaborator, hosted by Le Song and Sungsoo Ahn (Mar 2021 - May 2021)

Korea Advanced Institute of Science and Technology (KAIST)
Research Intern, hosted by Hongseok Yang (April 2018 - June 2019)

Honors and Awards

Recipient, Google Conference Scholarships (APAC), CVPR 2023
Top Reviewer, NeurIPS 2022
Best Paper Awards, Korean Artificial Intelligence Association, 2021
Recipient, KAIST Presidental Fellowship, 2018-2020
Recipient, Qualcomm-KAIST Innovation Awards, 2019
Recipient, National Presidental Scholarship for Science, 2017-2020
Recipient, Hansung Scholarship for Gifted Students, 2015-2016

Invited Talks

Efficient Generative Models for Videos
Mar 2023; LG AI Research (Seoul, South Korea)

RoMA: Robust Model Adaptation for Offline Model-based Optimization
Jun 2022; Samsung Electronics (Suwon, South Korea)

Scaling Video Generation via Implicit Neural Representations
Jun 2022; Pohang University of Science and Technology (Pohang, South Korea)

Abstract Reasoning via Logic-guided Generation
Jun 2021; ICML Workshop on Self-Supervised Learning for Reasoning and Perception 2021 (remote)

Academic Services

Conference reviewer: ICML'{22,23}, NeurIPS'{22,23}, ICLR'23, CVPR'23, ICCV'23
Workshop reviewer: AI4CC@CVPR'22, Neural-Fields@ICLR'23


Teaching Assistant, Deep Learning (AI502), Fall 2020
Teaching Assistant, Samsung Electronics Device Solutions, AI-Expert Program, Summer 2020
Peer Tutor, System Programming (CS230), Spring 2019
Teaching Assistant, Linear Algebra (MAS212), Spring 2019
Teaching Assistant, TA, Calculus 1 (MAS101), Spring 2018