22 septembre 2026 à 11h
Résumé :
With AI becoming increasingly capable, the bottleneck isn’t necessarily intelligence, it’s in how precisely users can communicate and direct the system. How can intelligent systems reduce the effort of expressing intent while preserving users’ ability to shape the outcome? In this talk, I’ll address this question through interfaces that combine machine intelligence with richer forms of human interaction. I will first discuss spatial XR interactions, showing how interactions can adapt to user intent inferred implicitly from multimodal signals. I will then turn to interactive AI systems for applications involving image, video, and 3D content demonstrating how users can exercise finer, more intuitive control over generative AI.
Bio :
Aakar Gupta is a Principal Researcher at Fujitsu Research of America where he works on Human-AI Interaction. Prior to this, he worked as a Research Scientist at Meta Reality Labs researching intelligent XR interactions. He did his PhD in Computer Science from University of Toronto. Aakar’s current research focuses on building user-aligned human-AI systems. His work has resulted in 40+ publications at top-tier HCI venues such as CHI and UIST including four Best Paper Honorable Mention Awards.
Inria, Amphi du bâtiment B
français
English