[–] jal278 1d ago ↗ 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 1d ago ↗ Is this just a theory about an architecture or are there actually some benchmarks/results to substantiate it?
[–] lstodd 1d ago ↗ I thought it's about https://en.wikipedia.org/wiki/Autotransformer [–] fc417fc802 1d ago ↗ I can't believe that actually works? This is far more interesting than the half baked ML idea.
[–] fc417fc802 1d ago ↗ I can't believe that actually works? This is far more interesting than the half baked ML idea.
5 comments
[ 4.0 ms ] story [ 18.8 ms ] thread