Large Language Models

Beyond Mamba SSMs: Parallel Kalman Filters as Scalable Primitives for Language Modelling featured image

Beyond Mamba SSMs: Parallel Kalman Filters as Scalable Primitives for Language Modelling

We show that Kalman filters can be reparameterized for efficient parallel training and introduces GAUSS, a more expressive yet equally scalable state-space layer that outperforms …

Vaisakh Shaj
Read more
An example preprint / working paper featured image

An example preprint / working paper

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

avatar
Aidan Scannell
Read more
An example conference paper featured image

An example conference paper

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

avatar
Aidan Scannell
Read more