AI Paper Atlas

Research map / Time series / Foundation models for time series

Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting

Siyuan Wang, Peng Chen, Yihang Wang, Wanghui Qiu, Chenjuan Guo, Bin Yang, Yang Shu

ICLR 2026 · Time series › Foundation models for time series · approach: LLM-based time series forecasting · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add event-driven reasoning and alignment to a time series model (ablation)VoT · Energy / Social GoodMSE: 0.250/0.944 -> 0.222/0.804Improved
Add endogenous text alignment (ETA) (ablation)VoT · Energy / Social GoodMSE: 0.241/0.840 -> 0.222/0.804Improved
Add historical in-context learning (HIC) (ablation)VoT · Energy / Social GoodMSE: 0.238/0.845 -> 0.222/0.804Improved
Add the event-driven branch with HIC guidance (ablation)VoT · Energy / Social GoodMSE: 0.232/0.841 -> 0.222/0.804Improved
Retrieve and summarize history rather than raw time series (full HIC vs time series retrieval) (ablation)HIC · ClimateMSE: 1.137 -> 1.078Improved
Retrieve raw time series instead of nothing (ablation)HIC · Social GoodMSE: 0.845 -> 0.853Hurt
Use exogenous text instead of random text (ablation)VoT event branch · EnergyMSE: 27.5% lower MSE and 14.3% lower MAEImproved
Use exogenous text instead of random text (ablation)VoT event branch · Social GoodMSE: 12.8% MSE reduction and 16.0% MAE reductionImproved
Use trend-seasonal decomposition in ETA (ablation)ETA · Social GoodMSE: 0.892 -> 0.841Improved
Add TS-Text contrastive learning to ETA (ablation)ETA · Social GoodMSE: 0.944 -> 0.841Improved
Use ETA instead of cross-attention for alignment (ablation)VoT · ClimateMSE: 1.202 -> 1.092Improved
Use 6-parameter adaptive frequency fusion instead of MLP (ablation)VoT · EnergyMSE: 0.685 -> 0.222Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy