Metraipolis › archive › dc_da70e84fee72

A 211K Parameter Foundation Model: Genetic Prompting in Neural Cellular Automata — arXiv:2610.38776

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.38776
License (as archived): CC0-1.0
Archived: 2026-11-01T02:41:45.662Z
SHA-256 of the archived text: 2ba703a37c89374d37eae05e8ae655a66e1b1468e859af8626fcd8eb3092647f
Stable URL of this page: https://metraipolis.com/documento/dc_da70e84fee72

How to cite

A 211K Parameter Foundation Model: Genetic Prompting in Neural Cellular Automata — arXiv:2610.38776 — arXiv (en), https://arxiv.org/abs/2610.38776 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da70e84fee72 (Metraipolis archive dc_da70e84fee72, sha256 2ba703a37c89374d37eae05e8ae655a66e1b1468e859af8626fcd8eb3092647f)

BibTeX

@misc{dcda70e84fee72,
  title = {A 211K Parameter Foundation Model: Genetic Prompting in Neural Cellular Automata — arXiv:2610.38776},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38776},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da70e84fee72; sha256 2ba703a37c89374d37eae05e8ae655a66e1b1468e859af8626fcd8eb3092647f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38776. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The scale of modern foundation models enables broad task generalization. In medical imaging, where segmentation demands vary widely across clinical contexts, such flexibility is invaluable. But current models, such as SAM trade adaptability for scale, locking their utility behind high-end infrastructure and leaving behind the low-resource environments most in need of diagnostic support. To bridge this gap, we introduce Foundational-NCA, a lightweight foundation model capable of adapting to a wide range of medical segmentation tasks without retraining. Built on Neural Cellular Automata (NCA), Foundational-NCA incorporates gradient-based learning with genetic optimization over a latent task space, using a compact task vector to guide predictions. This enables dynamic adaptation via a genetic prompt mechanism, allowing the model to generalize across tasks while keeping the parameter count magnitudes lower at just 211 thousand, compared to SAM-based models with 38.9 to 636 million parameters. We evaluate Foundational-NCA on 15 trained and 6 entirely unseen segmentation tasks from the TotalSegmentator dataset, achieving an average Dice score of 84.5% on known tasks and 60.4% on unseen ones. These results demonstrate that task generalization is possible in ultra-compact models, laying the groundwork for resource-efficient, deployable foundation models in clinical environments where infrastructure is limited. By reducing model size by over 180 times, Foundational-NCA takes a step toward a more equitable future for medical AI, one where powerful tools are within reach of every healthcare setting.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.38776 — 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 2026-11-01T02:16:43.900Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).