Abstract:In-context learning (ICL) enables task adaptation at inference time by conditioning on demonstrations rather than updating model parameters. Although recent time-series foundation models incorporate contextual conditioning, retrieval, or example-based prompting, they typically rely on implicit positional structure or task-specific objectives rather than explicit instruction-conditioned input-output demonstrations. We introduce iAmTime, a time-series foundation model trained with instruction-conditioned amortized meta-learning to infer tasks directly from example demonstrations. iAmTime represents each episode as a structured prompt over historical context and future-known variables using specialized semantic tokens that attend to designated time-series regions, exchange information across demonstrations, and inject task information into the query representation. The model combines a Hierarchical Multi-Scope Transformer Encoder, which captures temporal and covariate dynamics while inferring latent task structure from demonstrated input-output mappings, with a Task-Conditioned Patch Decoder, which adapts decoding through expert-based routing. We train iAmTime on large-scale real and synthetic corpora using supervised and self-supervised instruction-conditioned tasks, including forecasting, imputation, reconstruction, classification, anomaly detection, and source de-mixing. Across diverse domains, frequencies, and horizons, iAmTime improves zero-shot adaptation over strong time-series foundation baselines on probabilistic and point forecasting benchmarks, while achieving competitive performance on non-forecasting tasks such as classification.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.22586 [cs.LG] |
| (or arXiv:2603.22586v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.22586 arXiv-issued DOI via DataCite |
From: Anish Saha [view email]
[v1]
Mon, 23 Mar 2026 21:24:41 UTC (109 KB)
[v2]
Fri, 8 May 2026 10:12:45 UTC (722 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。