Hello, I'm

Zhengxuan Wei

卫正轩

First-year Ph.D. Student @ Nanjing University

Generative Models World Models Multimodal Learning

About Me

I am a first-year Ph.D. student in Computer Science and Technology at Nanjing University. I received my B.Eng. degree from ShanghaiTech University. My research interests include Generative Models, World Models, and Multimodal Learning.

I am currently a research intern at Kuaishou's Kling Team, and previously interned at vivo's BlueImage Lab.

🔥 News

2026.07 One paper conditionally accepted to SIGGRAPH Asia 2026.
2026.05 One paper accepted to ICML 2026.
2026.02 Joined Kuaishou Kling Team as a research intern.
2025.12 Awarded National Scholarship (Top 0.5%).
2025.10 Joined vivo BlueImage Lab as a research intern.
2025.06 Three papers accepted to ICCV 2025.

Selected Publications (First & Co-First Author)

(* indicates equal contribution)

ContextMaster paper thumbnail

arXiv 2026

ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Xu Guo*, Zhengxuan Wei*, Xinghui Li*, Hanzhuo Huang, Xinyu Liu, Xiangyang Luo, Min Wei, Yiran Zhu, Qiulin Wang, Yulong Xu, Xintao Wang, Pengfei Wan, Qi Fan, Xiangwang Hou

Paper Project

GIM-World paper thumbnail

SIGGRAPH Asia 2026

Geometry-Aware Implicit Memory for Video World Models

Zhengxuan Wei*, Xu Guo*, Xinghui Li*, Xunzhi Xiang, Min Wei, Yiran Zhu, Qiulin Wang, Xintao Wang, Pengfei Wan, Xiangwang Hou, Qi Fan

Paper Project

SSR-Merge paper thumbnail

ICML 2026

SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models

Zhengxuan Wei, Yi Dong, Zonghui Li, Xianhui Lin, Xing Liu, Hong Gu, Shaofeng Zhang, Wenbin Li, Qi Fan

Paper Code 量子位

AMR paper thumbnail

ICCV 2025

Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning

Zhengxuan Wei*, Jiajin Tang*, Sibei Yang

Paper Code

Sim-DETR paper thumbnail

ICCV 2025

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

Jiajin Tang*, Zhengxuan Wei*, Yuchen Zhu, Cheng Shi, Guanbin Li, Liang Lin, Sibei Yang

Paper Code

LoopTrans paper thumbnail

ICCV 2025

Closed-Loop Transfer for Weakly-supervised Affordance Grounding

Jiajin Tang*, Zhengxuan Wei*, Ge Zheng, Sibei Yang

Paper Code

Other Publications

VideoWeave paper thumbnail

arXiv 2026

VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling

Xunzhi Xiang, Zixuan Duan, Yabo Chen, Zhengxuan Wei, Guiyu Zhang, Zixiao Gu, Zhe Gao, Haibin Huang, Chi Zhang, Qi Fan, Xuelong Li

Paper Project

SimCIS paper thumbnail

CVPR 2025

Rethinking Query-based Transformer for Continual Image Segmentation

Yuchen Zhu*, Cheng Shi*, Dingyou Wang, Jiajin Tang, Zhengxuan Wei, Yu Wu, Guanbin Li, Sibei Yang

Paper Code

Education

Nanjing University

Current

Ph.D. in Computer Science and Technology

School of Intelligence Science and Technology

Advisor: Prof. Qi Fan

2026.09 – 2031.07 (expected)

ShanghaiTech University

B.Eng. in Computer Science and Technology

School of Information Science and Technology

GPA: 3.88/4.0 | Rank: 2/162

Advisor: Prof. Sibei Yang

2022.09 – 2026.07

Internships

Kuaishou — Kling Team

Current

Research Intern

Topic: Video generation and world models

Advisor: Xinghui Li, Xintao Wang

2026.02 – Present

vivo — BlueImage Lab

Research Intern

Topic: Image generation and editing

Advisor: Yi Dong

2025.10 – 2026.01

Honors

2026 Shanghai Outstanding Graduate

2026 ShanghaiTech President's Award

2025 National Scholarship (Top 0.5% among all undergraduates)

2025 ShanghaiTech Merit Student

2024 ShanghaiTech Outstanding Student

Contact

Feel free to reach out — I'm always open to interesting conversations and collaborations.

652026710025@smail.nju.edu.cn github.com/nagara214