Metraipolis › archive › dc_af4f1e310dec
Instance-Adaptive Prompts as Context for Time-Series Foundation Models — arXiv:2609.34786
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34786
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:36.528Z
- SHA-256 of the archived text
a01c81caaf267c1456bb413c857c48e90e8db98befbc5359f62c6a013ee3115a- Stable URL of this page
https://metraipolis.com/documento/dc_af4f1e310dec
How to cite
Instance-Adaptive Prompts as Context for Time-Series Foundation Models — arXiv:2609.34786 — arXiv (en), https://arxiv.org/abs/2609.34786 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af4f1e310dec (Metraipolis archive dc_af4f1e310dec, sha256 a01c81caaf267c1456bb413c857c48e90e8db98befbc5359f62c6a013ee3115a)
BibTeX
@misc{dcaf4f1e310dec,
title = {Instance-Adaptive Prompts as Context for Time-Series Foundation Models — arXiv:2609.34786},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34786},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af4f1e310dec; sha256 a01c81caaf267c1456bb413c857c48e90e8db98befbc5359f62c6a013ee3115a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34786. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual information can be provided more efficiently through a compact set of learned token embeddings. We introduce PaCTS, which generates a small set of instance-adaptive latent prompts in the form of continuous embedding tokens conditioned on the visible context. These prompts serve as compact context surrogates for frozen TSFMs. PaCTS constructs them from instance-specific global statistics and further refines them with segment-level temporal information, capturing both global characteristics and local temporal variations. The prompt module is jointly trained and deployed across heterogeneous time series with the frozen backbone. Extensive experiments demonstrate the effectiveness of prompts as context, consistently improving forecasting across context lengths and model architectures. With a shorter input context, PaCTS can outperform the same frozen backbone using double context while requiring substantially less inference computation. Compared with weight-space adaptation methods, PaCTS achieves stronger improvements and better out-of-distribution generalization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.34786 — 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 2026-10-07T22:14:28.288Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).