Model Architecture & Training MethodsBo Peng et al.
RWKV
RWKV
Why it matters
Restructured the RNN so it can be trained at Transformer level; the opening signal of a revival of linear complexity
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2305.13048Added in Week 35, 2026 · See that week