TimeFound: A Foundation Model for Time Series Forecasting

2025-03-06 · Congxi Xiao, Jingbo Zhou, Yixiong Xiao, Xinjiang Lu, Le Zhang, Hui Xiong

We present TimeFound, an encoder-decoder transformer-based time series foundation model for out-of-the-box zero-shot forecasting. To handle time series data from various domains, TimeFound employs a multi-resolution patching strategy to capture complex temporal patterns at multiple scales. We pre-train our model with two sizes (200M and 710M parameters) on a large time-series corpus comprising both real-world and synthetic datasets. Over a collection of unseen datasets across diverse domains and forecasting horizons, our empirical evaluations suggest that TimeFound can achieve superior or competitive zero-shot forecasting performance, compared to state-of-the-art time series foundation models.

📄 PDF Abstract BibTeX arXiv:2503.04118

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Patching Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process

Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting

2026-02-19 · Xinghong Fu, Yanhong Li, Georgios Papaioannou, Yoon Kim arxiv

Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insofar as scaling has been a critical driver of performance of f…

Time Series Forecasting Data Augmentation

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

2023-10-12 · Kashif Rasul, Arjun Ashok, Andrew Robert Williams, Hena Ghonia 외

Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-shot and few-shot generalization. However, despite the success of foundation models…

Decoder Probabilistic Time Series Forecasting Time Series Time Series Forecasting+1

Toto: Time Series Optimized Transformer for Observability

2024-07-10 · Ben Cohen, Emaad Khwaja, Kan Wang, Charles Masson 외

This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state…

Time Series Time Series Forecasting

How Foundational are Foundation Models for Time Series Forecasting?

2025-10-01 · Nouha Karaouli, Denis Coquenet, Elisa Fromont, Martial Mermillod 외 arxiv

Foundation Models are designed to serve as versatile embedding machines, with strong zero shot capabilities and superior generalization performance when fine-tuned on diverse downstream tasks. While this is largely true …

Time Series Forecasting

In-Context Fine-Tuning for Time-Series Foundation Models

2024-10-31 · Abhimanyu Das, Matthew Faw, Rajat Sen, Yichen Zhou

Motivated by the recent success of time-series foundation models for zero-shot forecasting, we present a methodology for $\textit{in-context fine-tuning}$ of a time-series foundation model. In particular, we design a pre…

Time Series