Metraipolis › archive › dc_c7e1981c7e93
Latent Inference-Time Guidance of Time Series Foundation Models — arXiv:2609.38058
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38058
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:33:13.007Z
- SHA-256 of the archived text
a0bb00fb38470bcfcfebdfa7f0a91bf9a93bf87d43666fe1cc4d8ac5a0a049d3- Stable URL of this page
https://metraipolis.com/documento/dc_c7e1981c7e93
How to cite
Latent Inference-Time Guidance of Time Series Foundation Models — arXiv:2609.38058 — arXiv (en), https://arxiv.org/abs/2609.38058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7e1981c7e93 (Metraipolis archive dc_c7e1981c7e93, sha256 a0bb00fb38470bcfcfebdfa7f0a91bf9a93bf87d43666fe1cc4d8ac5a0a049d3)
BibTeX
@misc{dcc7e1981c7e93,
title = {Latent Inference-Time Guidance of Time Series Foundation Models — arXiv:2609.38058},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38058},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7e1981c7e93; sha256 a0bb00fb38470bcfcfebdfa7f0a91bf9a93bf87d43666fe1cc4d8ac5a0a049d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time Series Foundation Models (TSFMs) currently provide state-of-the-art results in forecasting tasks. They are available out-of-the-box and rely on in-context learning to make their predictions, which makes the quality of their performance highly sensitive to the user-selected lookback, covariates, horizon and training data distributions. In practise, the quality of the forecasts are variable but complementary, which highlights the need for a principled ensembling approach, rather than selecting the best context. This paper introduces Latent Inference-Time Guidance for TSFMs, which adaptively combines a pool of TSFM forecasts through a time-dependent latent space with independent components. The framework comes equipped with identifiability and reconstruction guarantees, whilst maintaining the off-the-shelf aspect of foundation models. We provide experiments on datasets at various frequencies and from multiple domains: these show that the approach is competitive with traditional ensembling approaches. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2609.38058 — 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 2026-10-07T16:59:48.598Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).