Preprint
Jul 2026
Extending LLM Context via Associative Recurrent Memory
An extensive experimental study is presented demonstrating that ARMT-augmented models process inputs well beyond their original context limits without degrading performance relative to in-limit baselines and need 30% less FLOPs while preserving baseline performance within the original context window.
Gleb Kuzmin, I. Rodkin, A. Bulatov et al.
· 0 citations