Research map / Time series / Foundation models for time series
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
Lehui Li, Yuyao Wang, Jisheng Yan, Wei Zhang, Jinliang Deng, Haoliang Sun, Zhongyi Han, Yongshun Gong
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add temporal evolution semantic space with gating (TESS) (ablation) | PatchTST forecaster · Bitcoin | MSE: 4.2238 -> 2.2726 | Improved |
| add temporal evolution semantic space with gating (TESS) (ablation) | PatchTST forecaster · FNSPID | MSE: 0.0018 -> 0.0012 | Improved |
| add temporal evolution semantic space with gating (TESS) (ablation) | PatchTST forecaster · Electricity | MSE: 0.0298 -> 0.0230 | Improved |
| add confidence-aware gating (ablation) | TESS · Bitcoin | MSE: 2.3556 -> 2.2726 | Improved |
| add confidence-aware gating (ablation) | TESS · FNSPID | MSE: 0.0015 -> 0.0012 | Improved |
| add confidence-aware gating (ablation) | TESS · Electricity | MSE: 0.0248 -> 0.0230 | Improved |
| add distribution shift primitive (ablation) | TESS · FNSPID | MSE: +33% MSE when removed | Improved |
| use signal-only text instead of full text (redundancy removed) | direct text-time-series fusion · Semi-synthetic FNSPID | MSE | Improved |
| supply numerical feature vectors instead of signal-only text | direct text-time-series fusion · Semi-synthetic FNSPID | MSE: 0.0021 -> 0.0012 | Improved |
| TESS vs best baseline on Environment | TESS · Environment | MSE: 0.3472 -> 0.3534 | Hurt |
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.
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 3 of 3 shared results
- TimeLLM — Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024) · better on 1 of 1 shared result
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
- Context is Key: A Benchmark for Forecasting with Essential Textual Information (ICML 2025 · similarity 0.91)
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop (NeurIPS 2025 · similarity 0.90)
- $S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting (ICML 2024 · similarity 0.88)
- STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis (AAAI 2025 · similarity 0.88)
- Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting (NeurIPS 2026 · similarity 0.88)
- Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting (ICML 2025 · similarity 0.88)
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.
