Junyi Chen

Junyi Chen

Graduate of Computer Science

Sun Yat-sen University


I’m currently a graduate student at Sun Yat-sen University and major in CS.

I was a XCPCer and insterested in Programming Contest.

Now, I mainly focus on following topics:

  • Computer Vision
  • Multimodal (especially Vision + Language)
  • Artificial Intelligence
  • Computer Vision
  • Vision + Language
  • Programming Contest
  • BS in Computer Science, 2018

    Shanghai University

  • MS in Computer Science, 2022

    Sun Yat-sen University


Quickly discover relevant content by filtering publications.


ByteDance AI-Lab Speech & Audio
Software Enginner
ByteDance AI-Lab Speech & Audio
Jun 2021 – Oct 2020 Shanghai, China
Develop Adaptive Learning Engine in C++.
ByteDance AI-Lab Applied Vision
Algorithm Enginner
ByteDance AI-Lab Applied Vision
Mar 2022 – Present Shanghai, China
  • Computer Vision & Multimodal:
    • Large-scale Multi Label Image CLassification Model
    • Multimodal Multi Label Video Classification Model
    • Vision-Language Foundation Model
  • Ads Field (Douyin CTR Model):
    • Co-train with Content Discrete Tokens
    • Online Cluster and Offline Cluster
    • Architecture Improvement: Mixer-DIn