profile photo

| | |

Sihyun Yu

I am a final-year Ph.D. candidate at KAIST, advised by Jinwoo Shin, and a visiting scholar at NYU working with Saining Xie. 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.

News
Jun 2025: I am attending CVPR in person. See you in Nashville!
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!
Publications  
Selected
All

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie
ICLR 2025
Oral Presentation (213/11672=1.82%)
paper  |  project page  |  code

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
Sihyun Yu, Meera Hahn, Dan Kondratyuk, Jinwoo Shin, Agrim Gupta, José Lezama, Irfan Essa, David Ross, Jonathan Huang
CVPR 2025 Workshop on AI for Content Creation
Oral Presentation / Best Presentation Award
paper

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Sihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin, Anima Anandkumar
ICLR 2024
paper  |  project page  |  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

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 Presentation
paper  |  slide  |  poster

Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance
June Suk Choi, Kyungmin Lee, Sihyun Yu, Yisol Choi, Jinwoo Shin, Kimin Lee
preprint.
paper  |  project page

Learning Flexible Forward Trajectories for Masked Molecular Diffusion
Hyunjin Seo*, Taewon Kim*, Sihyun Yu, Sungsoo Ahn
preprint.
paper  |  project page

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie
ICLR 2025
Oral Presentation (213/11672=1.82%)
paper  |  project page  |  code

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
Sihyun Yu, Meera Hahn, Dan Kondratyuk, Jinwoo Shin, Agrim Gupta, José Lezama, Irfan Essa, David Ross, Jonathan Huang
CVPR 2025 Workshop on AI for Content Creation
Oral Presentation
paper

Controllable Human Image Generation with Personalized Multi-Garments
Yisol Choi, Sangkyung Kwak, Sihyun Yu, Hyungwon Choi, Jinwoo Shin
CVPR 2025
paper  |  project page  |  code

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
CVPR 2025
paper  |  project page  |  code

MC2: Multi-view Consistent Depth Estimation via Coordinated Image-based Neural Rendering
Subin Kim, Seong Hyeon Park, Sihyun Yu, Kihyuk Sohn, Jinwoo Shin
CVPR 2024 Workshop on Neural Rendering Intelligence
paper  |  project page

Data-Efficient Molecular Generation with Hierarchical Textual Inversion
Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin
ICML 2024
paper  |  code

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Sihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin, Anima Anandkumar
ICLR 2024
paper  |  project page  |  code

Learning Large-scale Neural Fields via Context Pruned Meta-Learning
Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin, Jonathan Richard Schwarz
NeurIPS 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

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

Work Experience

Google Research
Student Researcher (host: Jonathan Huang)
Oct 2023 - Apr 2024, Kirkland, WA

NVIDIA Research
Research Intern (mentors: Weili Nie, De-An Huang, Boyi Li, and Anima Anandkumar)
Mar 2023 - Sep 2023, Santa Clara, CA (remote)

Google Research
University Relation Program (host: Kihyuk Sohn)
Jul 2022 - Jan 2023, Bay Area, CA (remote)

Honors and Awards

Recipient, ICLR 2025 Google Conference Scholarships (APAC)
Winner, Qualcomm Innovation Fellowship Korea 2023
Recipient, CVPR 2023 Travel Awards
Recipient, CVPR 2023 Google Conference Scholarships (APAC)
Top Reviewer, NeurIPS 2022
Best Paper Awards, Korean Artificial Intelligence Association, 2021
Recipient, KAIST Presidental Fellowship
Recipient, 2019 Qualcomm-KAIST Innovation Awards
Recipient, National Presidental Scholarship for Science
Recipient, Hansung Scholarship for Gifted Students

Invited Talks

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
Jun 2025; CVPR 2025 Workshop on AI for Content Creation (Nashville, TN)

Training Diffusion Transformers Is Easier Than You Think
Apr 2025; ICLR 2025 Oral Session (Singapore)
Mar 2025; Sheffield NLP Group (Remote)
Feb 2025; KAIST Graduate School of AI (Seoul, South Korea)
Feb 2025; Korea AI Frontier Lab (Seoul, South Korea)
Dec 2024; Sungsoo Ahn's Group @ KAIST (Seoul, South Korea)
Oct 2024; BioImaging, Signal Processing & Learning Lab @ KAIST (Seoul, South Korea)

Efficient Latent Video Diffusion Models via Triplane Encoding
Nov 2023; Google Research (Kirkland, WA)

Video Probabilistic Diffusion Models in Projected Latent Space
Jun 2023; Innerverz (remote)

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'22-25, NeurIPS'22-25, ICLR'23-25, CVPR'23-25, ICCV'23-25, ECCV'24, WACV'25, AAAI'25, AISTATS'25
Workshop organizer: INR-V@CVPR'24

Teaching

Teaching Assistant, Deep Learning, Fall 2020
Teaching Assistant, Samsung Electronics AI-Expert Program, Summer 2020
Peer Tutor, System Programming, Spring 2019
Teaching Assistant, Linear Algebra, Spring 2019
Teaching Assistant, Calculus 1, Spring 2018