avatar

Chao Liao | 廖超

Researcher
Bytedance Seed | Prev Kuaishou Technology
1404177386@qq.com


About Me

Chao Liao is currently a Full-Time Researcher at ByteDance Seed. He received his B.S. from Shenzhen University (SZU) and his M.S. from Harbin Institute of Technology (HIT). He previously worked as a Research Intern at Peng Cheng Laboratory (PCL) and as a Full-Time Researcher at Kuaishou Technology.

Research Interests

His current research focuses on unified models for multimodal understanding and generation, with the primary research goal of exploring disruptive new paradigms for multimodal pre-training. His previous research covers neural architecture search (NAS) and multimodal large language models (MLLMs).

Selected Publications

  1. Seedream 4.0: Toward next-generation multimodal image generation
    Bytedance Seedream Team
    Bytedance Seed Tech Report, 2025.
    PDF

  2. Seed1.5-VL Technical Report
    Bytedance Seed Team
    Bytedance Seed Tech Report, 2025.
    PDF

  3. Mogao: An omni foundation model for interleaved multi-modal generation
    Chao Liao, Liyang Liu, Xun Wang, Zhengxiong Luo, Xinyu Zhang, Wenliang Zhao, Jie Wu, Liang Li, Zhi Tian, Weilin Huang
    Bytedance Seed Tech Report, 2025.
    PDF

  4. ICLR
    Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
    Yang Jin, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu
    International Conference on Learning Representations (ICLR), 2024.
    PDF Code

  5. ICLR
    Maskfusion: Feature augmentation for click-through rate prediction via input-adaptive mask fusion
    Chao Liao, Jianchao Tan, Jiyuan Jia, Yi Guo, Chengru Song
    International Conference on Learning Representations (ICLR), 2023.
    PDF

Academic Services

Conference Reviewers


Powered by Jekyll and Minimal Light theme.