ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning
Summary: ChatTS models multivariate time series as a modality for a multimodal LLM, trained solely on synthetic data via attribute‑based series generation and Time Series Evol‑Instruct QA. Outperforms vision/text LLMs on alignment and reasoning benchmarks (≈46% and 26% gains) and open‑sources code, checkpoints, and datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhe Xie
- 2. Zeyan Li
- 3. Xiao He
- 4. Longlong Xu
- 5. Xidao Wen
- 6. Tieying Zhang
- 7. Jianjun Chen
- 8. Rui Shi
- 9. Dan Pei
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,956 | D-Bot: Database Diagnosis System using Large Language Models | 2024 | VLDB | 9.960627e-05 |
| 8,286 | OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting | 2023 | VLDB | 4.5435639e-05 |
Previous
Page 1 / 1
Next