Metraipolis › archive › dc_e791aceac9bc

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens — arXiv:2610.03001

Source
arXiv
Original
https://arxiv.org/abs/2610.03001
License (as archived)
CC0-1.0
Archived
2026-10-05T23:10:03.140Z
SHA-256 of the archived text
8633703a291d39d922b56b1ae136725ffaf21ce12b0baf2fbfb1402ee56dc654
Stable URL of this page
https://metraipolis.com/documento/dc_e791aceac9bc

How to cite

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens — arXiv:2610.03001 — arXiv, https://arxiv.org/abs/2610.03001 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e791aceac9bc (Metraipolis archive dc_e791aceac9bc, sha256 8633703a291d39d922b56b1ae136725ffaf21ce12b0baf2fbfb1402ee56dc654)
BibTeX
@misc{dce791aceac9bc,
  title = {Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens — arXiv:2610.03001},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03001},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e791aceac9bc; sha256 8633703a291d39d922b56b1ae136725ffaf21ce12b0baf2fbfb1402ee56dc654},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03001. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into their tokens, so every new session is an input they have never seen, and they fail to generalize to it. A tokenizer for new sessions needs a unit that every session shares and that carries behavior. Population activity offers such a unit. It evolves on a low-dimensional manifold that persists across neuronal turnover and across animals once sessions are aligned. This manifold changes regime at task events such as stimulus onset and movement onset. Within each regime the population occupies a state, the part of the manifold it spans between two events, and each state carries its own behavioral meaning. We propose Tokenization with States (TWS), which segments each trial, one repetition of the task, at these events and converts every state into tokens of population geometry, with no neuron or session embedding. On held-out International Brain Laboratory (IBL) sessions, TWS decodes movement even from regime boundaries that carry no information about the target, while a per-neuron foundation model pretrained on those sessions decodes at chance. Frozen after training on mice alone, TWS transfers to macaques and Utah arrays with only a linear probe. On reach direction, a target that its boundaries do not define, it achieves a Matthews correlation of 0.23, where the event time alone achieves $0.01$. For cross-session generalization, the token matters more than the model on top.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03001 — 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 2026-10-05T23:01:38.660Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).