Artificial Intelligence and Image Understanding Lab
Banner portrait of Chen, Jun-Cheng

Jun-Cheng Chen


Associate Research Fellow (Associate Professor)

I am an Associate Research Fellow at the Research Center for Information Technology Innovation, Academia Sinica, where I lead the Artificial Intelligence and Image Understanding Lab. My research spans machine learning, computer vision, and multimedia analysis, with a long-term vision of advancing intelligent systems from perception to action. We ultimately aim to develop trustworthy, robust, and human-centric AI systems that can perceive, reason, interact, and act effectively in the real world.


πŸ“
Address
No. 128, Sec. 2, Academia Rd., Nankang, Taipei 11529, Taiwan
πŸ“ž
Phone / Fax
Tel: +886-2-2787-2300 ext. 2356
Fax: +886-2-2785-2701

Education

β†’
  • Ph.D. in Computer ScienceUniversity of Maryland College Park, 2016
  • M.S. in Computer Science and Information EngineeringNational Taiwan University, 2006
  • B.S. in Computer Science and Information EngineeringNational Taiwan University, 2004
View all

Experience

β†’
  • Associate Research FellowAcademia Sinica, 2023 – Present
  • Assistant Research FellowAcademia Sinica, 2019 – 2023
  • Postdoctoral Research FellowUniversity of Maryland College Park, 2017 – 2019
View all

Research Interests

β†’
Machine Learning Computer Vision Multimodal Learning Trustworthy AI Generative AI Agentic AI Physical AI

Invited Talks

β†’
  • From Noise to Desired Visual with Control: Guided Diffusion for Some Image/Video Application National Tsing Hua University, 2026
  • From Noise to Desired Visual: Guided Diffusion for Some Image/Video Application National Taiwan University of Science and Technology, 2025
  • A Brief Overview of Recent Advancement of Generative AI and New Challenges to Deepfake Detection OpenMFC Workshop, 2023
View all

Selected Honors

β†’
  • CE Magazine Best Paper AwardICCE, 2025
  • Best Paper Award Third PlaceAPSIPA ASC, 2023
  • Career Development AwardAcademia Sinica, 2021
  • Best Technical Full Paper AwardACM MM, 2006
View all

Selected Publications

β†’
πŸ“„
GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing International Conference on Learning Representations (ICLR), 2026
πŸ“„
Towards More General Video-based Deepfake Detection through Facial Feature Guided Adaptation for Foundation Model IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
View all publications