研究人员开发了ORCA（在线残差上下文适应）方法，这是一种用于在黑盒环境中适应时间序列基础模型（TSFM）的新颖方法。该方法侧重于从基础模型的预测误差中学习，认识到这些误差取决于模型的输入和输出。该方法通过在五个最先进的TSFM和八个数据集上进行的大量实验得到了验证，证明了它在无需白盒访问的情况下提高了适应性能的有效性。 AI
影响 这项研究为仅在黑盒访问可用时适应复杂时间序列模型提供了一种新方法，有可能拓宽其在商业环境中的应用范围。
排序理由 该集群包含一篇详细介绍适应AI模型新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.14222v1 Announce Type: new Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-sou…
The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online …