cv

Work

  • 2026 - Present
    Researcher
    ByteDance Seed
    Researcher working on multimodal learning and post-training for visual generation.
  • 2025 - 2026
    Research Intern
    ByteDance Seed
    Research Intern focusing on post-training for video generation and unified multimodal models.
  • 2024 - 2025
    Research Intern
    School of Engineering, Westlake University
    Research Intern working on post-training optimization of multimodal large language models and diffusion models.

Education

  • 2022.09 - 2026.06

    Guangzhou, China

    Bachelor
    School of Future Technology, South China University of Technology
    Artificial Intelligence

Interests

Artificial Intelligence
Deep Generative Models
Reinforcement Learning
Diffusion Models
Multimodal Large Language Models