Zijian Zhou | 周子键

About Me

I am a PhD student at the Department of Informatics, King's College London, UK. I am also affiliated with King's Institute for Artificial Intelligence. Before joining KCL, I had a great time as an Algorithm Engineer at ByteDance and Horizon Robotics, respectively. I obtained my Bachelor of Engineering degree from South China University of Technology in 2018.

I am actively seeking a full-time research position based in US or UK, with a focus on controllable image and video generation, unified visual understanding and generation, and their applications.

Research Interests

I am dedicated to exploring how machines can achieve super intelligence, enabling them to see, understand, think, and create. My current research focuses on controllable image and video generation and unified visual understanding and generation.

News

2025.08 - One Paper (VLPrompt) accepted to IJCV 📄
2025.06 - Thrilled to start my internship at Meta again 🦾
2025.06 - I traveled to Nashville for CVPR 2025 ✈️
2025.05 - One Paper (MarDini) accepted to TMLR 📄
2025.02 - Two Papers (Leffa, MPDrive) accepted to CVPR 2025 📄
2024.12 - We open sourced Leffa (Code, Demo, Model) 🤗
2024.12 - One paper (GFSS-EKT) accepted to AAAI 2025 📄
2024.10 - I traveled to Milan for ECCV 2024 ✈️
2024.07 - Happy to be awarded CGAOSFSA 🎉
2024.07 - One paper (OpenPSG) accepted to ECCV 2024 📄
2024.06 - Thrilled to start my internship at Meta 🦾
2023.10 - I traveled to Paris for ICCV 2023 ✈️
2023.09 - One paper (TP-SIS) accepted to NeurIPS 2023 📄
2023.07 - One paper (HiLo) accepted to ICCV 2023 📄
2023.04 - We open sourced RelateAnything 🤗
2022.10 - I traveled to Tel Aviv for ECCV 2022 ✈️
2022.07 - I arrived in London and started my PhD 🍀

Selected Papers

OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

Zhaochong An, Menglin Jia, Haonan Qiu, Zijian Zhou, Xiaoke Huang, Zhiheng Liu, Weiming Ren, Kumara Kahatapitiya, Ding Liu, Sen He, Chenyang Zhang, Tao Xiang, Fanny Yang, Serge Belongie, Tian Xie

Technical Report [Paper] [Website]

Scaling Zero-Shot Reference-to-Video Generation

Zijian Zhou, Shikun Liu, Haozhe Liu, Haonan Qiu, Zhaochong An, Weiming Ren, Zhiheng Liu, Xiaoke Huang, Kam Woh Ng, Tian Xie, Xiao Han, Yuren Cong, Hang Li, Chuyan Zhu, Aditya Patel, Tao Xiang, Sen He

Technical Report [Paper] [Website]

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng, Xiao Han, Chuyan Zhu, Chenyang Zhang, Ding Liu, Juan-Manuel Perez-Rua, Sen He, Jürgen Schmidhuber, Wenhu Chen, Ping Luo, Wei Liu, Tao Xiang, Jonas Schult, Yuren Cong

Technical Report [Paper] [Website]

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Haozhe Liu, Ding Liu, Mingchen Zhuge, Zijian Zhou, Tian Xie, Sen He, Yukang Yang, Shuming Liu, Yuren Cong, Jiadong Guo, Hongyu Xu, Ke Xu, Kam-Woh Ng, Juan C Pérez, Tao Xiang, Wei Liu, Shikun Liu, Jürgen Schmidhuber

Technical Report [Paper]

Scaling Sequence-to-Sequence Generative Neural Rendering

Shikun Liu, Kam Woh Ng, Wonbong Jang, Jiadong Guo, Junlin Han, Haozhe Liu, Yiannis Douratsos, Juan C Pérez, Zijian Zhou, Chi Phung, Tao Xiang, Juan-Manuel Pérez-Rúa

Technical Report [Paper] [Website]

Learning Flow Fields in Attention for Controllable Person Image Generation

Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan-Manuel Pérez-Rúa, Aditya Patel, Tao Xiang, Miaojing Shi, Sen He

CVPR 2025 [Paper] [Code] [Demo] [Model]

Mardini: Masked Autoregressive Diffusion for Video Generation at Scale

Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan C Pérez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, Jürgen Schmidhuber, Juan-Manuel Pérez-Rúa

Transactions on Machine Learning Research (TMLR) [Paper] [Website]

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

Zijian Zhou, Zheng Zhu, Holger Caesar, Miaojing Shi

ECCV 2024 [Paper] [Code]

VLPrompt-PSG: Vision-Language Prompting for Panoptic Scene Graph Generation

Zijian Zhou, Holger Caesar, Qijun Chen, Miaojing Shi

International Journal of Computer Vision (IJCV) [Paper] [Code]

Text Promptable Surgical Instrument Segmentation with Vision-Language Models

Zijian Zhou, Oluwatosin Alabi, Meng Wei, Tom Vercauteren, Miaojing Shi

NeurIPS 2023 [Paper] [Code]

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

Zijian Zhou, Miaojing Shi, Holger Caesar

ICCV 2023 [Paper] [Code]

Projects

Leffa

Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan-Manuel Pérez-Rúa, Aditya Patel, Tao Xiang, Miaojing Shi, Sen He

[Code] [Demo] [Model]

RelateAnything

Zujin Guo, Bo Li, Jingkang Yang, Zijian Zhou (alphabetical order)

[Code]

Education

King's College London

2022.06 - Now. Ph.D. in Department of Informatics. Supervised by Prof. Tomasz Radzik and Dr. Holger Caesar

South China University of Technology

2014.09 - 2018.06. B.Eng. in School of Electronics and Information. Supervised by Prof. Shuangping Huang and Prof. Lianwen Jin

Experience

Meta

2025.06 - Now. Research Scientist Intern, GenAI. Supervised by Dr. Sen He

Project: Reference-to-Video Generation

Meta

2024.06 - 2024.12. Research Scientist Intern, GenAI. Supervised by Dr. Sen He

Project: Controllable Person Image Generation

GigaAI

2023.08 - 2024.06. Research Intern. Supervised by Dr. Zheng Zhu

Project: Open-set Panoptic Scene Graph Generation

King's College London

2022.10 - 2024.02. Research Assistant, Department of Informatics. Supervised by Prof. Miaojing Shi and Prof. Tom Vercauteren

Project: Medical Imaging, Cambridge-1

ByteDance

2020.08 - 2022.05. Algorithm Engineer, Search Ads Group. Supervised by Shuai Tao

Project: Multimodal Relevance Model for Search Ads Engine

Horizon Robotics

2018.07 - 2020.08. Algorithm Engineer, Department of Platform and Technology. Supervised by Zhizhong Su and Yuan Li

Project: Facial Landmark Detection and Pose Estimation, Face Anti-Spoofing

Horizon Robotics

2017.08 - 2018.07. Algorithm Intern, AIoT Group. Supervised by Zhizhong Su and Dr. Dalong Du

Project: Scene Text Spotting (both detection and recognition)

South China University of Technology

2015.12 - 2017.06. Research Assistant, School of Electronics and Information. Supervised by Prof. Shuangping Huang and Prof. Lianwen Jin

Project: Scene Text Detection

Academic Services

Serve as a conference reviewer for CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI
Serve as a journal reviewer for TPAMI, IJCV, TMI

Awards

2024 - Award for Outstanding Self-Financed Students Abroad, 6000 USD
2023 - Google Cloud Research Credits Program, Maximum reward 5000 USD
2019 - Horizon Robotics Annual Performance Evaluation, Outstanding (top 5%)
2017 - The 14th Guangdong Challenge Cup, Special prize (top award)
2016 - Guangdong Electronic Design Competition, First prize