How do computers interpret visual information? How can we extend distant viewing capabilities by integrating diverse forms of media such as photography and TV? What kinds of humanities insights are possible by analyzing computationally image, text, and sound?

This talk will introduce the foundational concepts and theory behind distant viewing, then demonstrate how multimodal Large Language Models (LLMs) expand our ability to interpret large-scale visual datasets and meaningful insights that inform research questions in media and visual culture studies. The presentation will conclude by showcasing the Distant Viewing Explorer—an open-access interface designed to facilitate multimodal distant viewing research and discovery.