Jinwoo Shin .
Previously, I was a research intern at NVIDIA GEAR hosted by Jim Fan and Yuke Zhu , and a student researcher at Google DeepMind hosted by Yinxiao Li .
My research interests lie in probabilistic machine learning, generative modeling, and representation learning, with a focus on visual generative models, e.g., visual understanding and generation. In particular, I am interested in building world models using video diffusion models, and applications to robotics policy.
Email: kyungmnlee (at) gmail (dot) com | Curriculum Vitae
📝 Publications
Selected
All
World Action Models are Zero-Shot Policies Seonghyeon Ye ,
Yunhao Ge ,
Kaiyuan Zheng ,
Shenyuan Gao ,
Sihyun Yu ,
George Kurian ,
Suneel Indupuru ,
You Liang Tan ,
Chuning Zhu ,
Jiannan Xiang ,
Ayaan Malik ,
Kyungmin Lee William Liang ,
Nadun Ranawaka ,
Jiasheng Gu ,
Yinzhen Xu ,
Guanzhi Wang ,
Fengyuan Hu ,
Avnish Narayan ,
Johan Bjorck ,
Jing Wang ,
Gwanghyun Kim ,
Dantong Niu ,
Ruijie Zheng ,
Yuqi Xie ,
Jimmy Wu ,
Qi Wang ,
Ryan Julian ,
Danfei Xu ,
Yilun Du ,
Yevgen Chebotar ,
Scott Reed ,
Jan Kautz ,
Yuke Zhu ,
Jim Fan ,
Joel Jang
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model John Won ,
Kyungmin Lee Huiwon Jang ,
Dongyoung Kim ,
Jinwoo Shin
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
Kyungmin Lee Sihyun Yu ,
Jinwoo Shin
Calibrated Multi-Preference Optimization for Aligning Diffusion Models
Kyungmin Lee Xiaohang Li ,
Qifei Wang ,
Junfeng He ,
Junjie Ke ,
Ming-Hsuan Yang ,
Irfan Essa ,
Jinwoo Shin ,
Feng Yang ,
Yinxiao Li
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models Kyungmin Lee Sangkyung Kwak ,
Kihyuk Sohn ,
Jinwoo Shin
DreamFlow: High-quality Text-to-3D generation by Approximating Probability Flow Kyungmin Lee Kihyuk Sohn ,
Jinwoo Shin
Improving Diffusion Models for Authentic Virtual Try-on in the Wild Yisol Choi ,
Sangkyung Kwak ,
Kyungmin Lee Jinwoo Shin
Trust Region Q Adjoint Matching
Yonghoon Dong ,
Kyungmin Lee Changyeon Kim ,
Jaehyuk Kim ,
Jinwoo Shin
World Action Models are Zero-Shot Policies Seonghyeon Ye ,
Yunhao Ge ,
Kaiyuan Zheng ,
Shenyuan Gao ,
Sihyun Yu ,
George Kurian ,
Suneel Indupuru ,
You Liang Tan ,
Chuning Zhu ,
Jiannan Xiang ,
Ayaan Malik ,
Kyungmin Lee William Liang ,
Nadun Ranawaka ,
Jiasheng Gu ,
Yinzhen Xu ,
Guanzhi Wang ,
Fengyuan Hu ,
Avnish Narayan ,
Johan Bjorck ,
Jing Wang ,
Gwanghyun Kim ,
Dantong Niu ,
Ruijie Zheng ,
Yuqi Xie ,
Jimmy Wu ,
Qi Wang ,
Ryan Julian ,
Danfei Xu ,
Yilun Du ,
Yevgen Chebotar ,
Scott Reed ,
Jan Kautz ,
Yuke Zhu ,
Jim Fan ,
Joel Jang
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim ,
Jimin Lee ,
Myungkoo Koo ,
Dongyoung Kim ,
Kyungmin Lee Changyeon Kim ,
Younggyo Seo ,
Jinwoo Shin
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model John Won ,
Kyungmin Lee Huiwon Jang ,
Dongyoung Kim ,
Jinwoo Shin
Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance
Junesuk Choi ,
Kyungmin Lee Sihyun Yu ,
Yisol Choi ,
Jinwoo Shin ,
Kimin Lee
HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
Myungkoo Koo ,
Daewon Choi ,
Taeyoung Kim ,
Kyungmin Lee Changyeon Kim ,
Younggyo Seo ,
Jinwoo Shin
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
Kyungmin Lee Sihyun Yu ,
Jinwoo Shin
Calibrated Multi-Preference Optimization for Aligning Diffusion Models
Kyungmin Lee Xiaohang Li ,
Qifei Wang ,
Junfeng He ,
Junjie Ke ,
Ming-Hsuan Yang ,
Irfan Essa ,
Jinwoo Shin ,
Feng Yang ,
Yinxiao Li
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
Junesuk Choi ,
Kyungmin Lee Jongheon Jeong ,
Saining Xie ,
Jinwoo Shin ,
Kimin Lee
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models Kyungmin Lee Sangkyung Kwak ,
Kihyuk Sohn ,
Jinwoo Shin
Improving Diffusion Models for Authentic Virtual Try-on in the Wild Yisol Choi ,
Sangkyung Kwak ,
Kyungmin Lee Jinwoo Shin
Discovering and Mitigating Visual Biases through Keyword Explanation
Kyungmin Lee Jinwoo Shin
DreamFlow: High-quality Text-to-3D generation by Approximating Probability Flow Kyungmin Lee Kihyuk Sohn ,
Jinwoo Shin
Collaborative Score Distillation for Consistent Visual Editing
Subin Kim* ,
Kyungmin Lee* Junesuk Choi ,
Jongheon Jeong ,
Kihyuk Sohn ,
Jinwoo Shin
S-CLIP: Semi-supervised Vision-Language Pre-training using Few Specialist Captions
Kyungmin Lee Jinwoo Shin
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam ,
Jihoon Tack ,
Kyungmin Lee Hankook Lee ,
Jinwoo Shin
RényiCL: Contrastive Representation Learning with Skew Rényi divergence
Kyungmin Lee Jinwoo Shin
Representation Distillation by Prototypical Contrastive Predictive Coding
Kyungmin Lee
📖 Educations
2022.09 - 2026.08 , KAIST, Ph.D. in Artificial Intelligence.2015.03 - 2019.02 , KAIST, B.S. in Mathematics, Electrical and Computer Engineering (Double major).
💻 Work Experience
2025.12 - 2026.06 , Research Intern @ NVIDIA GEAR, Remote.2024.07 - 2024.12 , Student Researcher @ Google DeepMind, Mountain View, CA, US.2023.02 - 2024.03 , University Relation Program @ Google Research, Remote.
🤝 Academic Services
Conference reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, BMCV, WACV, AAAI
Journal reviewer: TMLR, TPAMI
-%234682B4){kind=icon}
-%234682B4){kind=icon}
-%234682B4){kind=icon}
-%234682B4){kind=icon}
