11 points MayCXC 1 hour ago 3 comments
jal278 7 minutes ago | parent
not sure w/o context why this is important -- no results/implementation & i believe there are prior combinations of transformers/RNNs. but perhaps I'm missing the relevance/insight
dankai 7 minutes ago | parent
Is this just a theory about an architecture or are there actually some benchmarks/results to substantiate it?