ChatTS (time-series MLLM; Tsinghua NetMan + ByteDance)
Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
- Parameters
- 8B
- Signals
- Text, time series
- Form factor
- general_time_series
- License
- Code MIT (repo); ChatTS-8B weights Apache-2.0
- Year
- 2024
- Architecture
Time-series MLLM on a Qwen3-8B base
- Type
- Foundation model
- Modalities
- Texttime series
- Form factor
- General time series
- Parameters
- 8B
- Architecture
- Time-series MLLM on a Qwen3-8B base
- Venue
- Not reported
- Year
- 2024
- arXiv
- Not reported
- DOI
- Not reported
- Weights
- Open
- Licence
- Code MIT (repo); ChatTS-8B weights Apache-2.0
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Oct 17, 2026
- Updated
- Oct 18, 2026
Original description
This repository provides official implementation of ChatTS, along with the training datasets and checkpoints for *[VLDB’25] paper: ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning*. ChatTS is a Time Series Multimodal LLM (TS-MLLM) with question-answering capabilities that focuses on native understanding and reasoning over time series, just like vision/video/audio MLLMs.
See the Case Studies for more real-world applications and sample conversations.
Example application See figures/chat_example.png and the Case Studies section for real-world scenarios and conversation examples.
Verbatim fromGitHub· Description from the repository README; licence: MIT
How it works
- Architecture
- Time-series MLLM on a Qwen3-8B base
- Inputs
- Text, time series
- Approach
- time series llm · base model · VLDB 2025 · multimodal llm
Datasets
Cite
APA
ChatTS (time-series MLLM; Tsinghua NetMan + ByteDance). (2024).
BibTeX
@misc{chatts2024chatts,
title = {{ChatTS (time-series MLLM; Tsinghua NetMan + ByteDance)}},
year = {2024}
}Built from the hub record. Check it against the publisher before submitting.
History
Record updated
Added to the ChatPPG research hub