Hi, I'm Amila Silva.
I am a postdoctoral research fellow in artificial intelligence at the University of Melbourne, conducting research to enhance the robustness of multimodal machine learning frameworks and human-AI teams. I completed my Ph.D. at the University of Melbourne. My Ph.D. research focused on developing AI models to understand complex multi-modal environments, where the holistic view of real-world objects is conveyed using multiple forms that could be either raw sensory media (e.g., text and image) or any inferred forms (e.g., propagation network of a news article). I worked on a mixture of theory and applications during my Ph.D., with the latter focusing on misinformation detection and cross-modal recommendation systems.
I previously interned at Meta AI in Menlo Park and Amazon Science in Australia, focusing on GAN-based and diffusion-based deep generative models and their transfer learning capabilities for new applications. Before my PhD, I was a Machine Learning Research Engineer at the Living Analytics Research Centre, Singapore Management University, and Singapore University of Technology and Design, working on the applications of deep neural networks in natural language processing and graph learning.