Jun Chen

I am currently a Research Scientist at Meta AI. I earned my PhD from King Abdullah University of Science and Technology (KAUST), where I was fortunate to be advised by Prof. Mohamed Elhoseiny. My research focuses on multimodal learning and developing scalable, efficient models for vision-language understanding. My representative works include VisualGPT, MiniGPT-4, and MiniGPT-v2, among others.

Google Scholar  /  CV  /  GitHub  /  LinkedIn  /  Twitter

News
  • 2025-02 I joined Meta AI as a Research Scientist
  • 2024-5 Started Postdoc at KAUST and very looooong visa waiting
  • 2023-12 Had a wonderful internship in Meta (Sunnyvale)
  • 2023-11 I succeeded my PhD Defence
  • 2023-10 Our paper MiniGPT-v2 is released
  • 2023-07 Our paper (ZeroSeg) is selected by ICCV 2023
  • 2023-05 MiniGPT-4 team was interviewed by TheSequence and MiT Technology Review
  • 2023-04 MiniGPT-4 is repored by 机器之心 and 量子位
  • 2023-04 We released MiniGPT-4 and received github 10k stars in 3 days!
  • 2023-04 We released Video ChatCaptioner
  • 2023-03 We released ChatCaptioner
  • 2023-02 One paper (MammalNet) is selected by CVPR 2023
  • 2022-08 Had a wonderful internship in Meta (Menlo Park)
  • 2022-02 Two papers (VisualGPT and RelTransformer) are selected by CVPR 2022
  • 2020-02 Start my PhD journey with Mohamed Elhoseiny
  • 2018-08 Start my Master jounery in King Abdullah University of Science and Technology (KAUST).
Research