Profile
Bojia Zi

Bojia Zi

Final-year Ph.D. Candidate

The Chinese University of Hong Kong

Previously, I got my master's degree and bachelor's degree from Fudan University and Shandong University in 2022 and 2019, respectively. I am seeking research roles in video pretraining, unified multimodal models, and LLM pretraining.

Email Scholar GitHub LinkedIn

Background

Education & Experience

  1. The Chinese University of Hong Kong emblem
    Ph.D., The Chinese University of Hong Kong

    Supervisor: Kam-Fai Wong

  2. IDEA Research logo
    IDEA@CVR

    Research Intern, LLM PEFT

  3. Microsoft logo
    Microsoft

    Research Intern, VLM Pretraining

  4. Fudan University logo
    M.S., Fudan University

    Supervisors: Yu-Gang Jiang and Xingjun Ma

  5. Shandong University emblem
    B.Eng., Shandong University

    Supervisor: Weiguo Liu

Publications

Publications

My work spans video editing, LLM and multimodal generation, video object removal, deepfake detection, datasets, and efficient model adaptation.

2026 TMM Submission

RT-Remover: A Real-Time Video Object Removal by Composing Tracking and Removal in Auto-Regressive Diffusion Transformers

Bojia Zi, Penghui Ruan, Xianbiao Qi, Youze Huang, Rong Xiao, Kam-Fai Wong

Paper GitHub
2026 SigAsia Submission

RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing

Bojia Zi*, Xiaoyan Yang*, Yu Zhou, Lihan Zhang, Haibin Huang, Bin Liang, Kam-Fai Wong, Chi Zhang, Xuelong Li

Paper GitHub
2026 ICASSP

Adversarial Prompt Distillation for Vision-Language Models

Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun Ma, Yu-Gang Jiang

Paper GitHub
2025 NeurIPS

Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

Bojia Zi*, Penghui Ruan*, Marco Chen, Xianbiao Qi, Shaozhe Hao, Shihao Zhao, Youze Huang, Bin Liang, Rong Xiao, Kam-Fai Wong

Paper GitHub
2025 NeurIPS

MiniMax-Remover: Taming Bad Noise Helps Video Object Removal

Bojia Zi*, Weixuan Peng*, Xianbiao Qi, Jianan Wang, Shihao Zhao, Rong Xiao, Kam-Fai Wong

Paper GitHub
2025 AAAI

CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility

Bojia Zi, Shihao Zhao, Xiaokang Qi, Jianlong Wang, Yukai Shi, Qianyu Chen, Bin Liang, Kam-Fai Wong, Lei Zhang

Paper GitHub
2023 Preprint

Delta-lora: Fine-tuning high-rank parameters with the delta of low-rank matrices

Bojia Zi, Xiaokang Qi, Lingzhi Wang, Jianlong Wang, Kam-Fai Wong, Lei Zhang

Paper GitHub
2021 ICCV

Revisiting adversarial robustness distillation: Robust soft labels make student better

Bojia Zi*, Shihao Zhao*, Xingjun Ma, Yu-Gang Jiang

Paper GitHub
2020 ACM MM

Wilddeepfake: A challenging real-world dataset for deepfake detection

Bojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma, Yu-Gang Jiang

Paper GitHub
2026 CVPR

Refaçade: Editing Object with Given Reference Texture

Youze Huang*, Penghui Ruan*, Bojia Zi*, Xianbiao Qi, Jianan Wang, Rong Xiao

Paper GitHub
2026 ACM MM Submission

ScaleVid Geometry-Aware Object Scaling in Video without Explicit 3D Reconstruction

Youze Huang*, Penghui Ruan*, Bojia Zi*, Xianbiao Qi, Rong Xiao

Paper GitHub
2026 ICLR

CTRL&SHIFT: High-quality Geometry-Aware Object Manipulation in Visual Generation

Penghui Ruan*, Bojia Zi*, Xianbiao Qi, Youze Huang, Rong Xiao, Pichao WANG, Jiannong Cao, Yuhui Shi

Paper GitHub
2026 Preprint

JDM: Joint Distribution Modeling for Fine-Grained Text-to-Video Generation

Penghui Ruan, Bojia Zi, Xianbiao Qi, Youze Huang, Rong Xiao, Pichao WANG, Jiannong Cao, Yuhui Shi

Paper GitHub
2026 Preprint

Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unifying Understanding and Generation

Shihao Zhao, Yitong Chen, Zeyinzi Jiang, Bojia Zi, Shaozhe Hao, Yu Liu, Chaojie Mao, Kwan-Yee K. Wong

Paper GitHub
2025 ICLR

Bigr: Harnessing binary latent codes for image generation and improved visual representation capabilities

Shaozhe Hao, Xiaoxiao Liu, Xianbiao Qi, Shihao Zhao, Bojia Zi, Rong Xiao, Kai Han, Kam-Fai Wong

Paper GitHub
2025 ACM MM

BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos

Jiahao Lin, Weixuan Peng, Bojia Zi, Yifeng Gao, Xianbiao Qi, Xingjun Ma, Yu-Gang Jiang

Paper GitHub
2024 ECCV

Bridging different language models and generative vision models for text-to-image generation

Shihao Zhao, Shaozhe Hao, Bojia Zi, Huaizhe Xu, Kwan-Yee K Wong

Paper GitHub

Academic Service

Academic Service

Reviewer

  • ICCV 2025, NeurIPS 2025
  • ICLR 2025, ICLR 2026
  • SigAsia 2026, AAAI 2026, AAAI 2025

Awards

Awards

  • Qimingxingchen Scholarship
  • DFDC Competition Silver Medal
  • Shanghai Outstanding Graduates

Teaching

Teaching Assistantships

  • Probability for Engineering (SEEM 2760)
  • Information Management (SEEM 5730)
  • Information Systems Analysis and Design (SEEM 3430)
  • Engineering Innovation and Entrepreneurship (SEEM 3450)

Skills

Skills

PyTorch, TensorFlow, Caffe, Python

Mandarin (Native Speaker), English IELTS 7.0

Contact