LongConv
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural NetworksParallelizing Legendre Memory Unit TrainingSimplified State Space Layers for Sequence ModelingPretraining Without AttentionWhat Makes Convolutional Models Great on Long Sequence Modeling?Hungry Hungry Hippos: Towards Language Modeling with State Space ModelsHyena Hierarchy: Towards Larger Convolutional Language ModelsRWKVSimple Hardware-Efficient Long Convolutions for Sequence ModelingTime-aware large kernel convolutionsResurrecting Recurrent Neural Networks for Long SequencesCKConv: Continuous Kernel Convolution For Sequential DataFlexConv: Continuous Kernel Convolutions with Differentiable Kernel SizesTowards a General Purpose CNN for Long Range Dependencies in ND
PreviousWhy self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from SymmetriesNextLegendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
Last updated