Welcome to Foundation Models and Federated Learning research group.

This group is in the University of Technology Sydney, Australia. We are dedicated to exploring new methodologies and applications on foundation models and federated learning. We are passionate to share our research outcomes with the research community via publishing papers, giving talks, hosting workshops and seminars, and sharing thoughts via writing blog posts. We also enjoyed the discussion with industry partners to solve their practical challenges using our knowledge and methods, and then towards co-designing innovative applications. We have special interests in applying cutting-edge artificial intelligence technology to solve the challenges of science, cybersecurity, digital health, climate change, and sustainable environment.

Image 1: UTS Central, Building 2 (the image is sourced from the Internet)

Prompt engineering is a major way of using foundation models, e.g. ChatGPT. However, privacy-preserving on prompt learning would be a new risk of using foundation models. For example, a user can create some prompt using her/his own emails or private documents that should not be shared out of their own computers. For this case, federated learning will be a new mechanism to be integrated with prompt learning to provide a privacy-preserved use of foundation models.