associative memory 1curriculum learning 1efficient training 1long-context processing 1transformer models 1
From the 1 of 5 linked papers with an AI index.
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Extending LLM Context via Associative Recurrent Memory
Gleb Kuzmin, Ivan Rodkin, Aydar Bulatov +8
The paper introduces the Associative Recurrent Memory Transformer (ARMT) to enable large language models to handle much longer contexts with constant memory usage and reduced compu…
cs.CL2026
Semantic Chunking and the Entropy of Natural Language
Weishun Zhong, Doron Sivan, Tankut Can +2
The entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) have only recently approached. Thi…