Metraipolis › archive › dc_69bf460f2be4

Neurons Are All You Need — arXiv:2611.00186

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00186
License (as archived)
CC0-1.0
Archived
2026-11-03T11:00:36.123Z
SHA-256 of the archived text
9cd426fb8a1fedbf231eaa53e28c25718d480d061a961bbba0221e457e11d0e2
Stable URL of this page
https://metraipolis.com/documento/dc_69bf460f2be4

How to cite

Neurons Are All You Need — arXiv:2611.00186 — arXiv (en), https://arxiv.org/abs/2611.00186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69bf460f2be4 (Metraipolis archive dc_69bf460f2be4, sha256 9cd426fb8a1fedbf231eaa53e28c25718d480d061a961bbba0221e457e11d0e2)
BibTeX
@misc{dc69bf460f2be4,
  title = {Neurons Are All You Need — arXiv:2611.00186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69bf460f2be4; sha256 9cd426fb8a1fedbf231eaa53e28c25718d480d061a961bbba0221e457e11d0e2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

For decades, artificial neural networks have operated under the assumption that durable, learned capability resides exclusively in adaptive synaptic parameters, primarily due to the established neurobiology of synaptic connectivity. This design forces models to remain stateless during deployment, incurring well-known limitations such as catastrophic forgetting and expensive retraining. However, recent neurobiological research by Glanzman and colleagues, and others, shows that memories can be transferred between individual organisms in a synaptically independent manner. Inspired by this research, we sought to demonstrate memory transfer of persistent memory between AI model instances, leveraging a neurocentric version of memory. In this paper, we propose NURESA (Neural Unit with Retentive Self-Adaptive Architecture), a novel neural layer that eschews sole reliance on synaptic weight updating by introducing persistent intra-unit memory as a first-class, computational primitive. By structurally separating computation from persistent memory, NURESA enables autonomous memory accumulation and consolidation into transferable stores of memory registers. Experiments across MLP, GPT-2, and modern frontier models like Qwen2.5 demonstrate qualitatively new capability: zero-shot transfer of learned capability into a naive model instance without retraining or access to the original training data; this transfer is enabled by a sparse set of parameters in NURESA's memory register that the model selects on its own based on which neurons were most active. The memory transfer capability of NURESA also protects against domain loss when transformer models undergo learning via fine-tuning. Finally, the memory transfer process completes in approximately one minute even for transformer models with millions to billions of parameters, producing a transfer file orders of magnitude smaller than the original model.

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/2611.00186 — 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 2026-11-03T10:59:45.687Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).