Metraipolis › archive › dc_c567bb831295
TEMPO: Time Series Understanding via Discrete Tokenization — arXiv:2611.04482
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04482
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:38:42.763Z
- SHA-256 of the archived text
bedfc95c6811442915bc26526b43c2f674973ff21bbd4cf1258f780d88e00608- Stable URL of this page
https://metraipolis.com/documento/dc_c567bb831295
How to cite
TEMPO: Time Series Understanding via Discrete Tokenization — arXiv:2611.04482 — arXiv (en), https://arxiv.org/abs/2611.04482 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c567bb831295 (Metraipolis archive dc_c567bb831295, sha256 bedfc95c6811442915bc26526b43c2f674973ff21bbd4cf1258f780d88e00608)
BibTeX
@misc{dcc567bb831295,
title = {TEMPO: Time Series Understanding via Discrete Tokenization — arXiv:2611.04482},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04482},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c567bb831295; sha256 bedfc95c6811442915bc26526b43c2f674973ff21bbd4cf1258f780d88e00608},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04482. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time-series interpretation often requires both numerical observations and textual context. Integrating these inputs into a pretrained language model raises a representation question: how should a signal enter the model's token sequence? We present TEMPO, which extends an LLM's vocabulary with discrete codes from a context-aware Transformer tokenizer using finite scalar quantization. A frozen tokenizer maps four-step patches to a 625-code vocabulary; signal tokens, scale statistics, and text are then processed by the LLM's existing self-attention layers. Adaptation updates the new token embeddings and DoRA adapters. With a Qwen3-4B backbone and task-specific fine-tuning, TEMPO achieves macro-F1 scores of 89.0% on activity recognition, 85.0% on sleep staging, and 86.0% on bearing-fault diagnosis. Time-series question answering and qualitative bearing-diagnosis examples further illustrate how this interface combines signal representations with textual context. Together, these results demonstrate the utility of discrete vocabulary extension for time-series understanding. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.04482 — 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 2026-11-04T18:32:52.154Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).