Our mission is to enable machines to perceive and understand the real world, so they can intelligently generate multimodal contents and robustly perform in challenging tasks.
  • Machine Perception: data acquisition and processing
  • Artificial Intelligence: Multimodal Content Generation and Interactions

Machine Learning

We conduct researches on probabilistic learning and inference, kernel methods and deep Learning, esp. Multimodal Deep Networks

Computer Vision

We work on a wide range of computer vision problems including visual scene understanding, video analysis and understanding and multimodal data analysis

Artificial Intellgience

We are interested in building highly-efficient AI models to enable content generation, understanding and multimodal interactions


  • In what are we interested?

    • Machine Learning and Pattern Recognition
    • Computer Vision and Multimedia Computing
    • Artificial Intelligence for Multimodal Content Generation and Interaction
    • Data Mining and Knowledge Discovery
    • see more...

  • What are we doing?

    • Regularized Generative Adversarial Nets and Applications
    • Learning Transformation Equivariant Representations
    • Diffusion model and AIGC for 2D/3D/Multimodal data
    • Small Data Challenges in Big Data Era
    • Time-Series Analysis and Applications
    • Perception, Control, Decision-Making and Optimization in Smart City
    • see more...

  • Keep updated about our progress