Metraipolis › archive › dc_65d9875cd136

Continuous Memory Machines — arXiv:2610.07907

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.07907
License (as archived): CC0-1.0
Archived: 2026-10-07T11:19:16.749Z
SHA-256 of the archived text: 4aa42e62937200cbb54d4244d89b7e5cd07b76ce63899c9a44a252a5519060b0
Stable URL of this page: https://metraipolis.com/documento/dc_65d9875cd136

How to cite

Continuous Memory Machines — arXiv:2610.07907 — arXiv (en), https://arxiv.org/abs/2610.07907 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_65d9875cd136 (Metraipolis archive dc_65d9875cd136, sha256 4aa42e62937200cbb54d4244d89b7e5cd07b76ce63899c9a44a252a5519060b0)

BibTeX

@misc{dc65d9875cd136,
  title = {Continuous Memory Machines — arXiv:2610.07907},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07907},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_65d9875cd136; sha256 4aa42e62937200cbb54d4244d89b7e5cd07b76ce63899c9a44a252a5519060b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07907. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the memory capacity or separating timescales, but lack the combination of rapid neuron-level processing and longer-term retention found in biology. To that end, we introduce the Continuous Memory Machine (CMM), a recurrent architecture with matrix-valued short- and long-term memory states serving distinct functional roles. Building on the Continuous Thought Machine (CTM), the CMM's short-term memory tracks recent neural activity, with uniquely parameterized neuron-level models learning to use these activity patterns for computation. A persistent long-term memory stores information for later use, with a Transformer jointly updating both memory stores, providing an expressive bidirectional read--write mechanism such that each store can reorganize its own contents and both read from and write to the other. Across algorithmic, in-context learning, and recurrent reasoning tasks, the CMM outperforms a broad suite of baselines, exhibiting stronger generalization than prior memory-augmented networks while preserving the CTM's interpretable attention patterns. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.07907 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:15:24.568Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).