AI 中文总结
研究时间序列基础模型预训练不足以可靠部署下游任务的问题，基于预测管道干预位置分析训练后处理方法，分为五类并研究其代表性方法与局限，确定未来方向，提供统一框架助于相关研究。
AI 中文摘要
时间序列基础模型（TSFMs）已成为用于时间序列分析的通用模型，但仅预训练通常不足以进行可靠的下游部署。弥合这一差距需要进一步干预以处理域转移、任务异质性、监督有限和计算约束等问题，这促使训练后处理成为一类广泛的方法，用于为下游任务调整、增强、组合、校准或专门化预训练的TSFMs。在这项工作中，我们根据它们在预测管道中的干预位置分析了TSFM训练后处理方法，产生了五类：参数适应、上下文增强、模型组合、输出处理和不确定性控制，以及压缩和专门化。在每个类别中，我们研究了主要的代表性方法并讨论了它们当前的局限性。我们进一步确定了朝着可控适应、可靠上下文构建、不确定性感知模型组合、校准输出处理和部署感知专门化的未来方向。总体而言，通过为新兴的TSFM训练后处理格局提供一个统一框架，这项工作旨在支持未来的研究，以在预训练的TSFM与其可靠的下游部署之间的设计空间中导航。
英文摘要
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize pretrained TSFMs for downstream tasks. In this work, we analyze TSFM post-training methods based on their locus of intervention in the prediction pipeline, yielding five categories: parameter adaptation, context augmentation, model composition, output processing and uncertainty control, and compression and specialization. Within each category, we study main representative methods and discuss their current limitations. We further identify future directions toward controlled adaptation, reliable context construction, uncertainty-aware model composition, calibrated output processing, and deployment-aware specialization. Overall, by providing a unifying framework for the emerging TSFM post-training landscape, this work aims to support future research to navigate the design space between a pretrained TSFM and its reliable downstream deployment.
