Research Areas (with selected publications, projects are linked [here])

 Artificial Intelligence and Foundation Models

o    Large Model Pretraining (Unsupervised/Semi-Supervised) [pdf] [pdf] [pdf]

o    Multimodal Representation Learning  [pdf] [pdf]

o    Diffusion Models [pdf] [pdf] [pdf] [pdf] and Generative Adversarial Network [pdf] [pdf]

o    Model Security and Privacy in Deep Learning [pdf] [pdf]

o    Network Architecture Search and Model Acceleration&Compression [pdf] [pdf[pdf] [pdf] [pdf]

 

Computer Vision and AIGC

o    AIGC-based Video and Image Generations [pdf][pdf]

o    Video/Image Analysis and Understanding [pdf] [pdf]

o    AI-enabled digital avatar modeling and animation [link[pdf] [pdf]

o    2D/3D Scene Reconstruction, Mapping and Localization [pdf] [pdf]

 

 

Internet-of-Things (IOTs) Information Processing and Analytics 

o    Discovery of trustworthy sources/sensors [pdf] [pdf]

o    Multi-source information fusion [pdf] [pdf]

o    Heterogeneous sensor data analysis [pdf] [pdf]


 

Back to top

Last updated 12/17/14