AI RESEARCH
Parallel Recursive LSTM
arXiv CS.LG
•
ArXi:2605.17108v1 Announce Type: new Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. However, the resulting quadratic time and memory costs limit efficiency in long-context settings. Recurrent models such as LSTMs provide explicit nonlinear state updates and strong state-tracking capabilities, yet their strictly sequential computation limits parallelism. We