Jul 2026
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Sparse Delta Memory is introduced, an architecture that scales the hidden state of gated linear RNNs to orders of magnitude higher capacity using a sparse addressing scheme and significantly improves performance on in-context learning and long-context retrieval tasks.
Loïc Cabannes, Pierre-Emmanuel Mazaré, Gergely Szilvasy et al.
· arXiv.org · 5 citations