Associative Recurrent Memory Transformer

This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is based on transformer self-attention for local context and segment-level recurrence for storage of task specific information distributed over a long context. We demonstrate that ARMT outperfors existing alternatives in associative retrieval tasks and sets a new performance record in the recent BABILong multi-task long-context benchmark by answering single-fact questions over 50 million tokens with an accuracy of 79.9%. The source code for training and evaluation is available on github.

@article{rodkin2025_2407.04841,
  title={ Associative Recurrent Memory Transformer },
  author={ Ivan Rodkin and Yuri Kuratov and Aydar Bulatov and Mikhail Burtsev },
  journal={arXiv preprint arXiv:2407.04841},
  year={ 2025 }
}