Xuan Ju Ph.D. Candidate Computer Science and Engineering The Chinese University of Hong Kong E-mail  /  CV  /  Google Scholar  /  Github

Biography

Hi, I'm Xuan Ju (鞠璇). I am currently a third-year Ph.D. student in the CURE Lab at The Chinese University of Hong Kong guided by Pro. Qiang Xu. Before this, I majored in Computer Science and Technology (minored in Mathematics and Applied Mathematics) and got my bachelor's degree from Tongji University.

I have a broad interest in most areas of computer vision, especially in image/video generation and multi-modal models. Please do not hesitate to reach out to me via email at juxuan.27@gmail.com !

Selected Publications

* equal contribution

	Teletubbies: On Design Choices of Scaling Autoregressive Models for Image Generation Yushi Hu*, Xuan Ju*, Xu Ma*, Yujun Shi*, Xiaoliang Dai, Peizhao Zhang, Jialiang Wang, Ji Hou, Yen-Cheng Liu, Haochen Zhang, Tao Xu, Felix Juefei-Xu, Ching-Yao Chuang, Zecheng He, Junjiao Tian, Tingbo Hou, Peter Vajda, Qiang Xu, Yun Fu, Vincent Y. F. Tan, Mari Ostendorf, Noah A. Smith, Zijian He, Sam Tsai, Kunpeng Li, Chih-Yao Ma. Under Review
	MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions Xuan Ju*, Yiming Gao*, Zhaoyang Zhang*, Ziyang Yuan, Xiantao Wang, Ailing Zeng, Yu Xiong, Qiang Xu, Ying Shan. Conference on Neural Information Processing Systems (NeurIPS), 2024 Project / Paper / arXiv / Video / Code / Data
	BrushNet : A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion Xuan Ju, Xian Liu, Xiantao Wang, Yuxuan Bian, Ying Shan, Qiang Xu. European Conference on Computer Vision (ECCV), 2024 Project / Paper / arXiv / Video / Code / Data
	Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, Qiang Xu. International Conference on Learning Representations (ICLR), 2024 Project / Paper / arXiv / Video / Code / Data
	HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation Xuan Ju*, Ailing Zeng*, Chenchen Zhao*, Jianan Wang, Lei Zhang, Qiang Xu. IEEE/CVF International Conference on Computer Vision (ICCV), 2023 (Oral, Top 1.8%) Project / Paper / arXiv / Video / Code / Data
	Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes Xuan Ju*, Ailing Zeng*, Jianan Wang, Qiang Xu, Lei Zhang. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Project / Paper / arXiv / Video / Code / Data
	Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning Yuxuan Bian*, Xuan Ju*, Jiangtong Li*, Zhijian Xu, Dawei Cheng, Qiang Xu. International Conference on Machine Learning (ICML), 2024 Paper / arXiv /

Experiences

	Research Intern, Kuaishou Kling Topic: Multimodal Video Generation Supervised by: Xintao Wang
	Research Intern, Meta GenAI Topic: Multimodal Image Generation Supervised by: Kevin Chih-Yao Ma
	Research Intern, Tencent ARC Laboratory Topic: Image Inpainting, Video Generation Supervised by: Xintao Wang, Ying Shan
	Research Intern, International Digital Economy Academy (IDEA) CVR Laboratory Topic: Human-Centric Image Generation Supervised by: Ailing Zeng, Lei Zhang
	Research Intern, X-Lab, SenseTime Research Topic: Human Pose Estimation Supervised by: Lei Yang

Professional Services

• Conference Reviewer for ICLR (2025), ECCV(2024), IJCV(2024), CVPR (2024, 2025), ICCV (2023), NeurIPS (2023, 2024), AAAI (2024), AISTATS (2025), ACCV (2024), WACV (2025).
• Organize CVPR 2025 workshop: 2nd Workshop on Efficient and On-Device Generation (EDGE).

Selected Honors & Awards

• National Scholarship
  2020, 2021
• Outstanding Graduate of Shanghai Province
  2022
• Qidi Scholarship
  2022
• First Prize in "Challenge Cup" National College Students Contest
  2022

Teaching Experience

• CSCI 1120, Introduction to Computing Using C++
  Fall 2023
• CSCI 1520, Computer Principles and C++ Programming
  Spring 2022
• CSCI 1540, Fundamental Computing with C++
  Fall 2022