This talk explores XAVIER, a novel integration of explainable  AI and VR designed to enhance radiology. The discussion focuses on combining AI’s predictive models with VR’s interactive capabilities to improve trust, reduce bias, and make diagnostic processes more transparent. Key topics include using eye-tracking data to study radiologists’ cognitive patterns, the role of multimodal systems like MDF-Net for combining clinical data with imaging, towards immersive radiology reading rooms. We will also address practical applications in training and global health, showcasing how AI and VR tools can bring advanced diagnostic capabilities to underserved regions while equipping radiologists with better tools to manage complex cases.

Our ability to recognize an object amongst many others is one of the most important features of the human mind. However, object recognition requires tremendous computational effort, as we need to solve a complex and recursive environment with ease and proficiency. This challenging feat is dependent on the implementation of an effective organization of knowledge in the brain. Here I put forth a novel understanding of how object knowledge is organized in the brain, by proposing that the organization of object knowledge follows key object-related dimensions, analogously to how sensory information is organized in the brain. Moreover, I will also put forth that this knowledge is topographically laid out in the cortical surface according to these object-related dimensions that code for different types of representational content – I call this contentopic mapping. I will show a combination of fMRI and behavioral data to support these hypotheses and present a principled way to explore the multidimensionality of object processing.

In the ever-evolving field of digital content creation, the demand for high-quality, diverse, and scalable character generation presents unique challenges to traditional workflows. This talk explores how workflow automation serves as the invisible thread, integrating creativity, efficiency, and scalability into the digital character creation pipeline. Attendees will uncover how advanced automation techniques streamline processes like modeling, rigging, texturing, and animation while maintaining unique artistic styles and meeting diverse technical specifications. The session will also highlight innovations in generating infinite character variations, optimizing memory usage, and enhancing rendering performance. Beyond showcasing current capabilities, this keynote aims to inspire new ways of thinking about unresolved challenges and opportunities in automation. Attendees will leave with a deeper understanding of how technology is reshaping the boundaries of creativity and problem-solving in the digital creation process, paving the way for future innovations in scalability and artistry.