cs.LGNov 4, 2026

Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models

Authors: Yuqian Wu, Qingxiang Liu, Yuxin Guo, Weifeng Su, Jian Li, Pengfei Xu, Xi Chen, Yutao Yue, 

Organizations: DSA Thrust, The Hong Kong University of Science and Technology (Guangzhou) · Solar System of OVB, Tencent, Guangzhou, China · INTR Thrust, The Hong Kong University of Science and Technology (Guangzhou) · Beijing Information Science and Technology University, Beijing, China · 

Abstract

Time series forecasting is critical for demand prediction and resource management in modern Web services, yet applying pretrained Time Series Foundation Models (TSFMs) to downstream tasks remains challenging due to domain shifts. Existing retrieval-augmented approaches typically retrieve coarse-grained window contexts and may introduce context-specific noise. To address this problem, we argue that temporal patterns should be reused at a decomposition level, as effective trend and seasonal dynamics may originate from different contexts. We propose \method, a two-stage Fine-grained Knowledge Augmentation framework that decouples and consolidates pre-training knowledge into compact, task-shared residual codebooks to enhance frozen TSFMs. Specifically, Stage I constructs dual-branch residual codebooks for decoupled trend and seasonal signals, while Stage II dynamically retrieves and merges these fine-grained patterns into target representations via task-adaptive aggregation and gate fusion. Extensive experiments across eight real-world benchmarks with four representative TSFM backbones demonstrate the superior effectiveness and computational efficiency of \method, while further validating the strong transferability of the residual codebooks across different backbones. The source code is available at the anonymous repository: https://github.com/yuppielqx/TSFM-Component-Token-Adapter

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification

    Oct 19, 2026Zhen Liu, Yucheng Wang, Yingpeng Du +5Time Series ClassificationTime-Series Foundation Models

  2. GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory

    Oct 4, 2026Xiaoyun Yu, Xiangfei Qiu, Yonggui Huang +7time series forecast correctionTime Series Forecasting

  3. A Survey of Post-Training in Time Series Foundation Models

    Jul 22, 2026Shifeng Xie, Ambroise Odonnat, Zehao Xiao +7Model CompressionTime-Series Foundation Models