Research paper / RESOURCE PROFILE

ChatTime: Unified Multimodal Time Series Foundation Model

Bridges numerical and textual modalities in a unified time-series foundation model.

Research & Papers
arxiv.orgPublished Dec 16, 2024
Visit source website ↗
Screenshot unavailableResource information and source links remain available. ChatTime: Unified Multimodal Time Series Foundation Model — reviewed source website screenshot
Reviewed source screenshot · recorded Oct 11, 2026 View source ↗

Overview

Bridges numerical and textual modalities in a unified time-series foundation model.

Topics & capabilities

foundation-modelpapermultimodal

Publication information

Publication title
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
Authors
Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Lei Zhang, Jianxin Liao
Published
Dec 16, 2024
Last publication revision
Dec 16, 2024
Subject areas
cs.CL, cs.LG
Publication source
arxiv.org · abs/2412.11376v1 ↗

Source: arXiv API · observed Oct 11, 2026.

Source links & provenance

https://arxiv.org/abs/2412.11376 ↗

Discovery references

References explain how this resource entered the collection. They do not represent an endorsement.

Explore related resources

Screenshot unavailableResource information and source links remain available. DeepIntoStreams/TSFM_Finance — reviewed source website screenshot
RepositoryChecked capture

DeepIntoStreams/TSFM_Finance

github.com

the official implementation of the paper “Re(visiting) Time Series Foundation Models in Finance”.

GitHub stars
31
Language
Jupyter Notebook
Code license
Apache-2.0
foundation-modeltime-seriesresearch-lab
Research & Papers Explore →
96 Authority 96 / 100 Cited by 2 resources in this directory 2 discovery sources Directory record updated: 2026-10-11 How scoring works →

Sign In

Don't have an account yet? Register

Forgot password?

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.