Saved in:
Bibliographic Details
Main Authors: Shastri, Hetvi, Sharma, Pragya, Hanafy, Walid A., Srivastava, Mani, Shenoy, Prashant
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.01038
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914175791398912
author Shastri, Hetvi
Sharma, Pragya
Hanafy, Walid A.
Srivastava, Mani
Shenoy, Prashant
author_facet Shastri, Hetvi
Sharma, Pragya
Hanafy, Walid A.
Srivastava, Mani
Shenoy, Prashant
contents Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK
format Preprint
id arxiv_https___arxiv_org_abs_2512_01038
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
Shastri, Hetvi
Sharma, Pragya
Hanafy, Walid A.
Srivastava, Mani
Shenoy, Prashant
Machine Learning
Artificial Intelligence
Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK
title FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.01038