Milad Khademi Nori, PhD

@khademinori

Postdoctoral Fellow @TorontoMet · Deep Learning (federated & continual learning) · PhD @QueensU

following
followers

RLM harnesses are claimed to help models generalize to similar unseen tasks 8–32 times longer than training tasks

The author says well-designed harnesses can make structurally similar tasks look nearly identical to individual model calls, even when the tasks come from different domains.

6 Sources, 37d ago, updated 37d ago

The claim that today’s state-of-the-art AI is neurosymbolic

A user says they agree with professor Gary Marcus that current state-of-the-art AI technology is neurosymbolic. Marcus reposted the comment.

2 Sources, 40d ago, first seen 40d ago

Featured in

RLM harnesses are claimed to help models generalize to similar unseen tasks 8–32 times longer than training tasks

The claim that today’s state-of-the-art AI is neurosymbolic

Featured in

RLM harnesses are claimed to help models generalize to similar unseen tasks 8–32 times longer than training tasks

The claim that today’s state-of-the-art AI is neurosymbolic