Ron Rothblum
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Efficient Scalable Oversight via Rewinding
According to the abstract, Ziyi Guan, Yael Tauman Kalai, Ron Rothblum, Zoe Xi and co-authors introduce rewindable interactive proofs, in which a weak verifier can rewind an AI prover to an earlier state. They construct a proof for certain computations that is more efficient than prior proofs not assuming a truthful prover.