Hi, I'm Yuxuan Bian (卞宇轩).

I am a Ph.D. candidate in the CURE Lab at The Chinese University of Hong Kong, guided by Prof. Qiang Xu. Before this, I majored in Computer Science and Technology, with a minor in Artificial Intelligence, and received my bachelor's degree from Tongji University.

My research focuses on Recursive Self Improvement and World Model. Please feel free to reach out at yuxuanbian23@gmail.com for collaboration or discussion!

Selected Research

* equal contribution

Echo-Infinity: Learnable Evolving Memory for Real-Time Infinite Video Generation

arXiv preprint, 2026

Yuxuan Bian, Zeyue Xue, Songchun Zhang, Shiyi Zhang, Weiyang Jin, Yaowei Li, Junhao Zhuang, Haoran Li, Jie Huang, Haoyang Huang, Nan Duan, Qiang Xu

Project Page

Paper Model

Video-As-Prompt: Unified Semantic Control for Video Generation

International Conference on Learning Representations (ICLR) 2026

Yuxuan Bian, Xin Chen, Zenan Li, Tiancheng Zhi, Shen Sang, Linjie Luo, Qiang Xu

Project Page

Paper Dataset

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) 2025

Yuxuan Bian, Zhaoyang Zhang, Xuan Ju, Mingdeng Cao, Liangbin Xie, Ying Shan, Qiang Xu

Project Page

Paper Dataset

BrushEdit: All-In-One Image Inpainting and Editing

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2026

Yaowei Li*, Yuxuan Bian*, Xuan Ju*, Zhaoyang Zhang, Junhao Zhuang, Ying Shan, Yuexian Zou, Qiang Xu

Project Page

Paper Dataset

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

AAAI Conference on Artificial Intelligence (AAAI) 2025

Yuxuan Bian, Ailing Zeng, Xuan Ju, Xian Liu, Zhaoyang Zhang, Wei Liu, Qiang Xu

Project Page

Paper Dataset

Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning

International Conference on Machine Learning (ICML) 2024

Yuxuan Bian*, Xuan Ju*, Jiangtong Li*, Zhijian Xu, Dawei Cheng, Qiang Xu

Project Page

Paper Dataset

BrushNet : A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

European Conference on Computer Vision (ECCV) 2024

Xuan Ju, Xian Liu, Xiantao Wang, Yuxuan Bian, Ying Shan, Qiang Xu

Project Page

Paper Dataset

Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code

International Conference on Learning Representations (ICLR) 2024

Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, Qiang Xu

Project Page

Paper Dataset

Internship

ByteDance Seed
Student Researcher
Topic: Recursive Self Improvement & World Model
Supervised by: Zihan Ding, Chaorui Deng, Haoqi Fan
Joy Future Academy, JD
Research Scientist Intern
Topic: World Model
Supervised by: Zeyue Xue, Nan Duan
Kuaishou Kling
Research Scientist Intern
Topic: Unified Understanding and Generation
Supervised by: Quande Liu, Xintao Wang
ByteDance Intelligent Creation Laboratory
Research Scientist Intern
Topic: Controllable Video Generation
Supervised by: Xin Chen, Linjie Luo
Tencent ARC Laboratory
Research Scientist Intern
Topic: Controllable Video Generation
Supervised by: Zhaoyang Zhang, Ying Shan
Luoshu Investment
Quant Research Intern
Topic: Portfolio Optimization