Metraipolis › archive › dc_f08fca56fa37
UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation — arXiv:2611.04825
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04825
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:37:19.118Z
- SHA-256 of the archived text
c45379817e7f95a4f5f65e36169d427b396213cc6bd85fa52fa9bfb0988cba6c- Stable URL of this page
https://metraipolis.com/documento/dc_f08fca56fa37
How to cite
UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation — arXiv:2611.04825 — arXiv (en), https://arxiv.org/abs/2611.04825 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f08fca56fa37 (Metraipolis archive dc_f08fca56fa37, sha256 c45379817e7f95a4f5f65e36169d427b396213cc6bd85fa52fa9bfb0988cba6c)
BibTeX
@misc{dcf08fca56fa37,
title = {UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation — arXiv:2611.04825},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04825},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f08fca56fa37; sha256 c45379817e7f95a4f5f65e36169d427b396213cc6bd85fa52fa9bfb0988cba6c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04825. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world time series exhibit complex dynamics across multiple temporal resolutions, yet effectively incorporating multi-scale information into generative modeling remains challenging without increasing generative complexity. We propose UniFlow, a unified framework that integrates multi-scale representation learning with efficient non-autoregressive generation through a shared-semantic discrete interface. Specifically, a multi-scale tokenizer employs shared-index voting to consolidate complementary temporal information into a single public-ID sequence, while scale-specific codebooks preserve the information required for reconstruction. Building on this unified representation, we develop geometry-aware categorical flow matching, which initializes transport from learned low-rank anchors and generates public identities non-autoregressively. This design captures multi-scale temporal structure without requiring multiple generative token streams or sequential token decoding. Experiments across four benchmarks and both short- and long-term settings demonstrate improved generative fidelity, strong cross-scale consistency, and substantial inference speedups over representative autoregressive and diffusion-based baselines. Code is available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04825 — 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 2026-11-04T18:32:37.467Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).