Metraipolis › archive › dc_34cc40412de5

GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals — arXiv:2609.27018

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27018
License (as archived)
CC0-1.0
Archived
2026-10-08T10:52:04.537Z
SHA-256 of the archived text
8a1549fa90c455644838e058e7544024011bd2286af9e59c620dac0ba4f3d83e
Stable URL of this page
https://metraipolis.com/documento/dc_34cc40412de5

How to cite

GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals — arXiv:2609.27018 — arXiv (en), https://arxiv.org/abs/2609.27018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34cc40412de5 (Metraipolis archive dc_34cc40412de5, sha256 8a1549fa90c455644838e058e7544024011bd2286af9e59c620dac0ba4f3d83e)
BibTeX
@misc{dc34cc40412de5,
  title = {GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals — arXiv:2609.27018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34cc40412de5; sha256 8a1549fa90c455644838e058e7544024011bd2286af9e59c620dac0ba4f3d83e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Residual vector quantization (RVQ) turns physiological waveforms into compact token sequences, but conventional masked modeling treats every incorrect token as equally costly. We propose GeoRVQ, a coarse-to-fine masked token model whose objective reflects the local response of a frozen waveform decoder. Decoder-induced costs define geometry-aware soft targets and expected distortion, while quantizer-causal prediction follows residual dependencies from coarse to fine levels. In a descriptive aggregate over MIMIC-IV Waveform, VitalDB, and CODE-15\%, GeoRVQ increases exact token accuracy from $.133\pm.004$ to $.143\pm.003$, reduces decoded distance from $.606\pm.006$ to $.393\pm.007$, and increases R-peak F1 from $.784\pm.004$ to $.837\pm.008$ under matched model and training conditions. Across 45 held-out code substitutions, decoder-induced cost has a Spearman correlation of $.85$ with realized decoded cost, compared with $.54$ for Euclidean codeword distance. These results indicate that decoder-aware objectives can improve waveform and event preservation without requiring a large increase in exact token accuracy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.27018 — 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 2026-10-08T10:06:16.695Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).