Abstract: The exponential growth of scholarly literature presents a significant challenge for researchers striving to stay abreast of the latest findings and synthesize knowledge effectively. This challenge is compounded by the rise of misinformation and the increasing complexity of scientific data. In this talk, I will first give an overview of our efforts in processing scientific documents to support scientific knowledge discovery, synthesis, and communication. Next, I will discuss our recent studies on reconstructing fallacies in misrepresented science and generating slides and scientific diagrams for presentation in more detail. Finally, I will outline several challenging research questions on modelling scholarly documents.