ChengXiang Zhai
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Do AI Scientists Know What's New?
According to the abstract, Liu, Zhao, Xie and Zhai build a framework for testing the novelty checks used in AI scientific-discovery pipelines, with 1,060 proposals. They report that checks good at rejecting non-novel work also reject many ideas later published, and introduce ClaimNov, a claim-level module.