KronLSTM applies a Kronecker Delta Rule to long-context linear attention
Authors report stable bounded memory without extra normalization, and open-source code and models are released.
1 stories, newest first · one card per story
Authors report stable bounded memory without extra normalization, and open-source code and models are released.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views