Yuxin Jiang

I am a Ph.D. student at National University of Singapore (NUS) and Agency for Science, Technology and Research (A*STAR), advised by Prof. Mike Zheng Shou and Prof. Ivor Tsang.

Previously, I received my B.Eng. in Computer Science with a Minor in Mathematics at Nanyang Technological University (NTU), Singapore, supervised by Prof. Chen Change Loy.

My research interests lie in computer vision and deep generative models for visual content creation. More recently, my research has shifted toward exploring the transformative potential of generative models in embodied AI, such as building video world models from natural data (e.g., raw videos), and modeling the causal and temporal structure underlying them, toward applications in games and robotics.

Email  /  Google Scholar  /  GitHub  /  Twitter  /  LinkedIn

profile photo
Publications
(* equal contribution)
StreamingEffect: Real-Time Human-Centric Video Effect Generation
Yiren Song, Cheng Liu, Yuxin Jiang, Mike Zheng Shou
arXiv Preprint,  2026
arXiv  /  Code GitHub Repo stars

Keywords: Streaming video effect generation
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang, Weijia Mao, Song Han, Han Cai, Mike Zheng Shou
European Conference on Computer Vision (ECCV),  2026
arXiv  /  Project Page  /  Code GitHub Repo stars

Keywords: Flow map models, Video diffusion distillation, OPD
Olaf-World: Orienting Latent Actions for Video World Modeling
Yuxin Jiang, Yuchao Gu, Ivor Tsang, Mike Zheng Shou
Forty-Third International Conference on Machine Learning (ICML),  2026
arXiv  /  Project Page  /  Code GitHub Repo stars

Keywords: Video world model, Latent action
MIND: Benchmarking Memory Consistency and Action Control in World Models
Yixuan Ye*, Xuanyu Lu*, Yuxin Jiang*, Yuchao Gu, Rui Zhao, Qiwei Liang, Jiachun Pan, Fengda Zhang, Weijia Wu, Alex Jinpeng Wang
arXiv Preprint,  2026
arXiv  /  Project Page  /  Code GitHub Repo stars

Keywords: World model Benchmark, Memory consistency, Action control
Personalized Vision via Visual In-Context Learning
Yuxin Jiang, Yuchao Gu, Yiren Song, Ivor Tsang, Mike Zheng Shou
ICCV Workshop on Personalization in Generative AI (P13N),  2025
arXiv  /  Project Page  /  Code GitHub Repo stars

Keywords: Personalization, Visual ICL, Diffusion transformer
Balanced Image Stylization with Style Matching Score
Yuxin Jiang, Liming Jiang, Shuai Yang, Jia-Wei Liu, Ivor Tsang, Mike Zheng Shou
International Conference on Computer Vision (ICCV),  2025 
arXiv  /  Project Page  /  Code GitHub Repo stars

Keywords: Style transfer, Diffusion model, Score distillation
Towards Efficient 3D Object Detection in Bird’s-Eye-Space for Autonomous Driving: A Convolutional-Only Approach
Yuxin Li, Qiang Han, Mengying Yu, Yuxin Jiang, Chai Kiat Yeo, et al.
IEEE International Conference on Intelligent Transportation Systems (ITSC),  2023 
arXiv

Keywords: 3D object detection, BEV, Autonomous driving
(Internship Project at Desay)
Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation
Yuxin Jiang*, Liming Jiang*, Shuai Yang, Chen Change Loy
International Conference on Computer Vision (ICCV),  2023 
arXiv  /  Project Page  /  Code GitHub Repo stars  /  Demo

Keywords: Scene stylization, GAN, Domain adaption
Education & Experiences
National University of Singapore (NUS) 📍 Singapore
Aug. 2024 - Present
Department of Electrical and Computer Engineering
Ph.D. Student
CGPA: 5.00 / 5.00
Visual AI Group, KAIST 📍 Daejeon, South Korea
Jan. 2024 - Mar. 2024
Student Researcher (Advisor: Prof. Minhyuk Sung)
Multimedia Laboratory (MMLab), NTU 📍 Singapore
Aug. 2021 - May. 2024
Algorithm Research Intern (Advisor: Prof. Chen Change Loy)
Nanyang Technological University (NTU) 📍 Singapore
Aug. 2020 - May. 2024
B.Eng. in Computer Science with a Minor in Mathematics
CGPA: 4.88 / 5.00 (Highest Distinction)
ntucs-repo🙈
Honors & Awards
Service

  • Conference Reviewer:  
    • ICCV’25, CVPR’26, ICML’26, ECCV’26, BMVC’26, NeurIPS’26
  • Workshop Reviewer:  
    • MIPI@CVPR’24, ActiVis@CVPR’26, VideoWorldModel@CVPR’26
  • Journal Reviewer:  
    • CVIU, IEEE TAI, IEEE TMM

    		•

    © Yuxin
    Template by Jon Barron.