CS Seminar: Jason Corso

Description

Jason Corso, a professor of electrical engineering and computer science at the University of Michigan, will give a talk titled "Curious Embeddings, Hazy Oracles, and the Path to Safe, Cooperative AI" for the Department of Computer Science.

Refreshments are available starting at 10:30 a.m. The seminar will begin at 10:45 a.m.

Abstract:

Cooperation through safe and trustworthy communication and interaction is fundamental to how human teams accomplish complex tasks. Yet, despite significant—and sometimes revolutionary—advances in artificial intelligence, we have barely begun to unlock the potential of safe, cooperative AI. This may stem from our limited understanding of how multimodal, large-scale AI models function; the one-sided nature of contemporary, fully supervised AI approaches; or social concerns about human-AI collaboration. In this talk, Jason Corso will delve into these layers of inquiry, beginning with a principled exploration of what the embeddings in large-scale foundation models reveal about the underlying problem and data, including new results disentangling sample-size from Bayes error and decision-boundary complexity. He will then introduce the concept of the human collaborator as a "hazy oracle"—a fallible partner rather than an omniscient information source—and establish a framework for modeling human-supplied error during collaboration. Building on these foundational insights, Corso will conclude with applications of these ideas to foster safe and effective human-AI collaboration in the health sciences.