Re:DenseFormer: Enhancing Information Flow in Transformers
by matteopagli on Saturday March 23, 2024 @09:55AM
(#39799970)
I'm one of the authors, happy to answer questions.
[ Parent
| on HN ]
Re:DenseFormer: Enhancing Information Flow in Transformers
by EvkoGS on Sunday March 24, 2024 @10:07AM
(#39807322)
Is it possible to combine your approach with NATTEN? It seems that both approaches are optimizing from different directions and can be combined with significant throughput and small performance improvements?