A team from Cornell led by Kevin Ellis, assistant professor of computer science in the Cornell Ann S. Bowers College of Computing and Information Science, has developed a set of AI models that together, solve about 56% of the problems – scoring within 4 percentage points of the average human. Their paper, “Combining Induction and Transduction for Abstract Reasoning,” received a first-place-paper award at the 2024 ARC Prize competition. Lead authors on the paper were Wen-Ding Li, a doctoral student in the field of computer science, and Keya Hu, a visiting undergraduate student in Ellis’ group.








