arXiv cs.AI· Zuyang Shen, Luqi Gong, Fanda Fan, Bingsong Wang, Xiang Ao, Yahui Wei, Minghao Liu, Chunjie Luo, Jianfeng Zhan·· 4 小时前AI 评分34
FlexCast:面向时间序列基础模型的灵活上下文学习框架
FlexCast: Flexible Context Learning for Time Series Foundation Models
AI 导读
FlexCast 是一个将变量上下文条件与自回归解码解耦的时间序列基础模型学习框架,把预测重构为对时间序列 patch 的可变长度掩码预测。在 BLAST 及多个零样本基准上,其精度与强 TSFM 基线持平或更优,同时显著降低推理延迟。消融实验表明收益来自上下文多样性与连续目标掩码,而非从左到右解码。
正文 · 原文
Abstract:Time series foundation models (TSFMs) based on autoregressive (AR) next-token prediction entangle two factors: variable-context conditioning and prediction-unit factorization with autoregressive rollout. Strong AR performance therefore does not reveal whether generalization stems from the flexible training distribution, the local prediction target, the left-to-right inference process, or their combination. We propose FlexCast, a flexible context-target learning framework that disentangles these factors. FlexCast reformulates forecasting as variable-length masked prediction over time series patches: during pretraining, it dynamically samples visible context and masked target patches, exposing the model to diverse context-target configurations without sequential decoding. At inference time, the same pretrained model supports one-step forecasting, confidence-based iterative refinement, and next-token-style generation through a unified mask-and-predict interface, enabling controlled comparison of inference schedules under identical architecture, data, and objective. Evaluated on BLAST and multiple zero-shot benchmarks, FlexCast achieves accuracy competitive with or better than strong TSFM baselines while substantially reducing inference latency. Ablations confirm that context diversity and contiguous target masking drive performance, while left-to-right decoding does not yield consistent gains once flexible context-target relationships have been learned, suggesting that the key benefit of AR-style TSFMs lies in flexible training rather than sequential inference. The code is available at this https URL.
| Comments: | 15 pages, 8 figures. Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17862 [cs.AI] |
| (or arXiv:2611.17862v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17862 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zuyang Shen [view email]
[v1]
Fri, 13 Nov 2026 07:50:25 UTC (455 KB)
来源:arXiv cs.AI · arxiv.org