view article Article Sliding window beats linear attention, but only on short answers sirluk • 18 days ago • 6
KronLSTM Collection The language models of the paper "Kronecker Delta Rule for Long Context Linear Attention" pretrained on 100B tokens. • 4 items • Updated about 1 month ago • 6
ParalESN: Enabling parallel information processing in Reservoir Computing Paper • 2601.22296 • Published Jan 29
ParalESN: Enabling parallel information processing in Reservoir Computing Paper • 2601.22296 • Published Jan 29
pLSTM: parallelizable Linear Source Transition Mark networks Paper • 2506.11997 • Published Jun 13, 2025 • 10
Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks Paper • 2508.21172 • Published Aug 28, 2025 • 1 • 2
Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks Paper • 2508.21172 • Published Aug 28, 2025 • 1