Yabo Zhang (张亚博)

I am a third-year Ph.D. student supervised by Prof. Wangmeng Zuo at Harbin Institute of Technology (HIT), and currently a research intern at the Seed team. Prior to this, I obtained my bachelor's and master's degrees in computer science from HIT in 2021 and 2023, respectively.

My research focuses on multimodal generation and language models. Academically, my works (e.g., ControlVideo and ELITE) have been published at top-tier conferences and have collectively garnered over one thousand citations and stars. On the industry side, I am deeply involved in the development of the Seedream series models.

I am actively seeking industry positions starting Spring 2027. Feel free to reach out!

Email  /  Wechat: YBYBZhang  /  Google Scholar  /  Github  /  Linkedin

profile photo
Selected Publications
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
Yabo Zhang, Kunchang Li, Dewei Zhou, Xinyu Huang, Xun Wang, Hui Li, Wangmeng Zuo
Seed Technical Report, 2025

Paper

FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors
Yabo Zhang, Xinpeng Zhou, Yihan Zeng, Hang Xu, Wangmeng Zuo
ICCV 2025

Paper | Code [500+ stars🌟] |

VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Yabo Zhang, Yuxiang Wei, Xianhui Lin, Zheng Hui, Peiran Ren, Xuansong Xie, Xiangyang Ji, Wangmeng Zuo
AAAI 2025

Paper | Code [150+ stars🌟] | Project Page

ControlVideo: Training-free Controllable Text-to-Video Generation
Yabo Zhang, Yuxiang Wei, Dongsheng Jiang, Xiaopeng Zhang, Wangmeng Zuo, Qi Tian
ICLR 2024

Paper | Code [800+ stars🌟] | Demo

VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization
Mingshuai Yao, Yabo Zhang, Xianhui Lin, Xiaoming Li, Wangmeng Zuo
AAAI 2024

Paper | Code

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation
Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, Wangmeng Zuo
ICCV 2023 (Oral)

Paper | Code [500+ stars🌟] | Demo

DiFa: Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
Yabo Zhang, Mingshuai Yao, Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Wangmeng Zuo
NeurIPS 2022

Paper | Code | Slides | Video

Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation
Yabo Zhang, Zihao Wang, Jun Hao Liew, Jiashi Feng, Manyu Zhu, Wangmeng Zuo
Arxiv 2023

Paper | Code

Internships
  • Bytedance Seed Vision, May.2025 - Now
    Mentored by Xun Wang and Weilin Huang.

  • Noah's Ark Lab, Jan.2025 - May.2025
    Mentored by Yihan Zeng and Hang Xu.

  • Bytedance Intelligent Creation, Jun.2022 - Jan.2023
    Mentored by Zihao Wang, work closely with Jiashi Feng and Jun Hao Liew.

  • Bytedance AILab, Apr. 2021 - Aug. 2021
    Focus on table detection and recognition in photo scene.
Service
  • Journal reviewers: TPAMI, TIP, TNNLS, TCSVT, Science China, Machine Learning
  • Conference reviewers: NeurIPS (2023, 2024, 2025), ICLR (2024, 2025), CVPR (2024, 2025), ICML (2024, 2025), ECCV 2024, AAAI 2025
Honors
  • China National Scholarship (2022)

  • Excellent Graduate at Harbin Institute of Technology (2021, 2023)

  • First-Class People's Scholarship (Top 3%)

  • Huawei Enterprise Scholarship (Top 3%)

  • Meritorious Winner in Mathematical Contest in Modeling (Top 7%)
Teaching

    Teaching assistant in Harbin Institute of Technology.

  • CS32262: Pattern Recognition Deep Learning, Spring 2022

  • CS32131: Data Structures and Algorithms, Fall 2021

Page template is take from this template.