Recently, we talked to Dan Fu and Tri Dao – authors of “Hungry Hungry Hippos” (aka “H3”) – on our Deep Papers podcast. H3 is a proposed language modeling architecture that performs comparably to ...
The STATESPACE procedure provides automatic model selection, parameter estimation, and forecasting of state space models. (State space models encompass an alternative general formulation of ...
For a while now, we’ve been talking about transformers, frontier neural network logic models, as a transformative technology, no pun intended. But now, these attention mechanisms have other competing ...
Researchers have introduced a new approach to sequence modeling called linear oscillatory state-space (LinOSS) models, designed for efficient learning on long sequences. Drawing inspiration from ...