# Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models

arXiv: https://arxiv.org/abs/2603.00629 · HTML: https://mlsanity.com/paper/2603.00629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance](https://mlsanity.com/paper/2304.11127/) (2023)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [Data Augmentation techniques in time series domain: A survey and taxonomy](https://mlsanity.com/paper/2206.13508/) (2022)
- [Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning](https://mlsanity.com/paper/1905.13628/) (2019)
- [Data augmentation using synthetic data for time series classification with deep residual networks](https://mlsanity.com/paper/1808.02455/) (2018)
- [When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection](https://mlsanity.com/paper/2312.11976/) (2023)
- [Impact of Data Normalization on Deep Neural Network for Time Series Forecasting](https://mlsanity.com/paper/1812.05519/) (2018)
- [How Far Should We Look Back to Achieve Effective Real-Time Time-Series Anomaly Detection?](https://mlsanity.com/paper/2102.06560/) (2021)
- [Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML](https://mlsanity.com/paper/2103.01992/) (2021)
- [Efficient Time Series Processing for Transformers and State-Space Models through Token Merging](https://mlsanity.com/paper/2405.17951/) (2024)

## Built on by (most cited first, 1 of 1)

- [Post-Training in Time Series Foundation Models: A Unifying Framework](https://mlsanity.com/paper/2607.20002/) (2026)

## Abstract (arXiv)

Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between forecasting accuracy and generalization. Rather than continually finetuning new LTM instances for each domain, we propose a data-centric framework, time-series adaptive transformation optimization (TATO), that enables a single frozen pre-trained LTM to adapt to diverse downstream domains through an optimally configured transformation pipeline. Specifically, TATO constructs three representative types of transformations, including context slicing, scale normalization, and outlier correction, to help LTMs better align with target domain characteristics. To ensure robustness, we incorporate carefully selected time series augmentations and a two-stage ranking mechanism that filters out pipelines underperforming on specific metrics. Extensive experiments on state-of-the-art LTMs and widely used datasets demonstrate that TATO consistently and significantly improves domain-adaptive forecasting performance, achieving a maximum reduction in MSE of 65.4% and an average reduction of 13.6%. Moreover, TATO is highly efficient, typically completing optimization in under 2 minutes, making it practical for real-world deployment. The source code is available at https://github.com/thulab/TATO.