News for hackers. Stuff that matters.
Re:Mamba: Linear-Time Sequence Modeling with Selective State... by smaddox on Monday December 04, 2023 @07:34PM (#38525452)
> If replicated, it's arguably the first linear-time architecture with Transformer-quality performance!!

RetNet was published in August (although I only learned of it last week): https://arxiv.org/abs/2307.08621

There are no comments on this comment yet.