FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines

• URL: http://arxiv.org/abs/2512.01038v1
• Date: Sun, 30 Nov 2025 19:14:04 GMT
• Title: FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
• Authors: Hetvi Shastri, Pragya Sharma, Walid A. Hanafy, Mani Srivastava, Prashant Shenoy,
• Abstract summary: Time-series foundation models (TSFMs) have shown strong performance on classification, regression, and imputation tasks.<n>Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance.<n>We introduce FMTK, an open-source, lightweight and implementations toolkit for constructing and fine-tuning TSFM pipelines.
• Score: 2.6650725474904617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• LFM2 Technical Report [87.58431408281973]
  We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities.<n>The LFM2 family covers 350M-8.3B parameters, including dense models (350M, 700M, 1.2B, 2.6B) and a mixture-of-experts variant (8.3B total, 1.5B active)<n>We build multimodal and retrieval variants: LFM2-VL for vision-latency tasks, LFM2-Audio for speech, and LFM2-ColBERT for retrieval.
  arXiv  Detail & Related papers  (2025-11-28T17:56:35Z)
• TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates [21.978694988304692]
  Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance in univariate forecasting on new time series.<n>We propose TFMAdapter, a lightweight, instance-level adapter that augments TSFMs with covariate information without fine-tuning.<n>Extensive experiments on real-world datasets demonstrate that TFMAdapter consistently outperforms both foundation models and supervised baselines.
  arXiv  Detail & Related papers  (2025-09-17T11:13:14Z)
• Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures [58.72593025539547]
  In this paper, we unveil an unexplored variation of M3T FFMs by proposing hierarchical federated foundation models (HF-FMs)<n>HF-FMs strategically align the modular structure of M3T FMs, comprising modality encoders, prompts, mixture-of-experts (MoEs), adapters, and task heads.<n>To demonstrate their potential, we prototype HF-FMs in a wireless network setting and release the open-source code for the development of HF-FMs.
  arXiv  Detail & Related papers  (2025-09-03T20:23:19Z)
• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models [67.95907033226585]
  Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting.<n>While naive finetuning can yield performance gains, we argue that it falls short of fully leveraging TSFMs' capabilities.<n>We propose Multiscale finetuning (MSFT), a simple yet general framework that explicitly integrates multi-scale modeling into the finetuning process.
  arXiv  Detail & Related papers  (2025-06-17T01:06:01Z)
• Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning [27.23328609888911]
  Time Series Foundation Models pre-train vast parameters and achieve remarkable zero-shot forecasting performance.<n>Surprisingly, even after fine-tuning, TSFMs cannot consistently outperform smaller, specialized models trained on full-shot downstream data.<n>We propose a structured pruning method to regularize the subsequent fine-tuning process by focusing it on a more relevant and compact parameter space.
  arXiv  Detail & Related papers  (2025-05-29T07:33:49Z)
• Enabling Time-series Foundation Model for Building Energy Forecasting via Contrastive Curriculum Learning [12.19823790689484]
  We study the adaptation of foundation models (FMs) to building energy forecasting tasks.<n>We propose a new textitcontrastive curriculum learning-based training method.<n>Experiments show that our method can improve the zero/few-shot performance by 14.6% compared to the existing FMs.
  arXiv  Detail & Related papers  (2024-12-23T05:07:06Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• A Survey on Efficient Federated Learning Methods for Foundation Model Training [62.473245910234304]
  Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. In the wake of Foundation Models (FM), the reality is different for many deep learning applications. We discuss the benefits and drawbacks of parameter-efficient fine-tuning (PEFT) for FL applications.
  arXiv  Detail & Related papers  (2024-01-09T10:22:23Z)
• Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction [2.412497918389292]
  We propose LeafFM model based on FM to generate new features from the original feature embedding by learning the transformation functions automatically. Experiments are conducted on three real-world datasets and the results show Leaf-FM model outperforms standard FMs by a large margin.
  arXiv  Detail & Related papers  (2021-07-26T08:29:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.