SymTime / README.md

whenxuan: update the readme

1ddb5c4 verified 5 days ago

3.62 kB

license: apache-2.0
metrics:
  - mse
  - mae
tags:
  - time series
  - forecasting
  - foundation models
  - pretrained models
  - generative models
  - time series foundation models
library_name: transformers
language:
  - en

SymTime NeurIPS 2025

This code is the official PyTorch implementation of our NeurIPS'25 paper: Synthetic Series-Symbol Data Generation for Time Series Foundation Models.

This repository contains the official Hugging Face / PyTorch implementation of SymTime from our NeurIPS 2025 paper, Synthetic Series-Symbol Data Generation for Time Series Foundation Models.

Overview

SymTime is a lightweight time series foundation model designed to learn strong temporal representations from patch-based inputs. It is built for practical downstream use and supports easy loading through the Hugging Face AutoModel interface.

The model takes a univariate time series, splits it into patches, and encodes the patch sequence with a transformer backbone. The repository includes the configuration, model definition, and a runnable example for inference.

Quick start

Install dependencies

pip install -r requirements.txt

Load the model

from transformers import AutoModel

model = AutoModel.from_pretrained("FlowVortex/SymTime", trust_remote_code=True)

Run inference

import torch

x = torch.randn(16, 256)
out = model(x)
out_no_cls = model(x, return_cls_token=False)

Model summary

Input: Tensor with shape [batch_size, seq_length]
Output: patch embeddings, optionally with a CLS token output
Backend: patch-based transformer encoder

Citation

If you find this code useful, please cite our paper.

@misc{wang2025syntheticseriessymboldatageneration,
      title={Synthetic Series-Symbol Data Generation for Time Series Foundation Models}, 
      author={Wenxuan Wang and Kai Wu and Yujian Betterest Li and Dan Wang and Xiaoyu Zhang},
      year={2025},
      eprint={2510.08445},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.08445}, 
}

Contact

If you have any questions or are interested in our view on the complex dynamics of time series, feel free to contact:

Acknowledgement

We appreciate the following GitHub repos a lot for their valuable code and efforts.

Time-Series-Library (https://github.com/thuml/Time-Series-Library)
PySDKit (https://github.com/wwhenxuan/PySDKit)
ALBEF (https://github.com/salesforce/ALBEF)
PatchTST (https://github.com/yuqinie98/PatchTST)
Short-term Forecasting (https://github.com/ServiceNow/N-BEATS)