Metraipolis › archive › dc_bb43d0c29d06

Distilling Neural Population Geometry into Transformers and GRUs for Motor Control — arXiv:2611.06931

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06931
License (as archived)
CC0-1.0
Archived
2026-11-06T14:57:16.498Z
SHA-256 of the archived text
7c19dcaeb1b7f3d064445e1d8b853ef7870937884a8dbc0a930d8461861ffeb8
Stable URL of this page
https://metraipolis.com/documento/dc_bb43d0c29d06

How to cite

Distilling Neural Population Geometry into Transformers and GRUs for Motor Control — arXiv:2611.06931 — arXiv (en), https://arxiv.org/abs/2611.06931 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb43d0c29d06 (Metraipolis archive dc_bb43d0c29d06, sha256 7c19dcaeb1b7f3d064445e1d8b853ef7870937884a8dbc0a930d8461861ffeb8)
BibTeX
@misc{dcbb43d0c29d06,
  title = {Distilling Neural Population Geometry into Transformers and GRUs for Motor Control — arXiv:2611.06931},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06931},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb43d0c29d06; sha256 7c19dcaeb1b7f3d064445e1d8b853ef7870937884a8dbc0a930d8461861ffeb8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06931. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce neuro-distillation (Neuro-Dist), a technique designed to directly transfer computationally useful neural population structure from biological brains into artificial controllers. Using three macaque motor-cortical datasets as neuro-distillation teachers, we align controller internal states with cortical neural population geometry during training; controller deployment requires no neural data. We evaluate gated recurrent unit (GRU) networks and Transformers controlling a simulated arm. Neuro-Dist achieves the lowest median error among five methods, including distillation from movement kinematics, in 10 of 18 comparisons across trained, student-held-out, and new target directions. Seed-split aggregate statistical comparisons significantly favor Neuro-Dist over all six controls on trained and new targets, and five on student-held-out targets (Holm-corrected familywise p<0.05). We furthermore find that Neuro-Dist can substantially improve controller robustness to sensory feedback noise. Mechanistically, Neuro-Dist induced low tangling of trajectories in internal controller state space---a functionally important characteristic of motor cortex, demonstrating successful transfer of a known motor-cortical population geometry feature. These findings establish neuro-distillation as a complement to behavioral distillation and point to a novel class of neuro-interfaces that tap biological neural population structure as a computational resource for improving the control of goal-directed behavior in robotics and embodied AI.

Tema degli esploratori: scienze della vita e salute (elenco arXiv q-bio.NC, nuovi lavori del giorno).
Categorie arXiv: Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2611.06931 — 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 2026-11-06T14:39:21.131Z dalla pagina https://arxiv.org/list/q-bio.NC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).