A new paradigm: Multimodal autonomous AI

Event date:  29 April 2021

Multimodal AI is bridging the gap between human and computer intelligence. As the future of technology, it’s enabling machines to combine various data types – such as images, text, speech and numbers – to achieve a richer, more holistic way of thinking and understanding.

In this Monash Tech Talks event hosted by Monash Information Technology, our Institute Director Prof Joanna Batstone joined a leading panel of specialists and industry experts to speak about:

  • low-level multimodal perception (vision and language), video/image understanding, automatic translation and multilingual systems, and higher-level reasoning for decision-making.
  • multimodal navigation in self-driving cars and other autonomous technology.
  • real-life applications and benefits of multimodal AI in healthcare, finance, retail, business and other sectors – with examples from eBay, Google, Amazon and more.
  • how multimodal AI can contribute to social good.


Ms Bernadette Schwerdt - Keynote speaker, author and entrepreneur


Associate Professor Reza Haffari - Lead, Vision and Language Group

Professor Joanna Batstone - Director, Monash Data Futures Institute

Dr Michelle Ananda-Rajah - Consultant physician General Medicine & Infectious Diseases, Alfred Health

View event page