Research map / Time series / Foundation models for time series
TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
Tong Guan, Zijie Meng, Dianqi Li, Shiyu Wang, Chao-Han Huck Yang, Qingsong Wen, Zuozhu Liu, Sabato Marco Siniscalchi, Ming Jin, Shirui Pan
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 CoT-SFT with reasoning traces instead of answer-only SFT (ablation) | TimeOmni-1 multi-task · Causality Discovery (ID) | accuracy: 30.5 -> 67.7 | Improved |
| add Stage 1 SFT on reasoning traces to the base model (ablation) | Qwen2.5-Instruct-7B · Task 2 Causality Discovery (ID) | accuracy: +46.1% | Improved |
| add human-guided templates to the zero-shot prompt (ablation) | GPT-4.1 · Task 2 Causality Discovery | consistency accuracy: 28.7 -> 71.1 | Improved |
| apply Stage 2 RL directly to the base model without Stage 1 SFT (ablation) | Qwen2.5-Instruct-7B · Task 4 Decision Making | accuracy: 5.3% drop | Hurt |
| add RL (Stage 2) after CoT-SFT (ablation) | TimeOmni-1 multi-task · Scenario Understanding (ID) | accuracy: 89.8 -> 90.7 | Improved |
| add RL after CoT-SFT on decision making (ablation) | TimeOmni-1 multi-task · Decision Making (ID) | accuracy: 40.9 -> 47.9 | Improved |
| use multi-task joint training instead of single-task training (ablation) | CoT-SFT+RL · TSR-Suite ID testbed, four tasks | accuracy / MAE: +8.2%, +1.8%, 2.46 (MAE), +7.0% | Improved |
| train decision-making jointly with perception and extrapolation tasks (ablation) | TimeOmni-1 · Decision Making (ID) | accuracy: 40.9 -> 45.7 -> 47.9 | Improved |
| zero-shot transfer from perception and extrapolation training to decision making (ablation) | base model · Decision Making (ID) | accuracy: 25.5 -> 26.2 -> 31.3 | Improved |
| add the counting bonus reward for sequence length | RL reward for event-aware forecasting · Task 3 Event-aware Forecasting | valid sequence length: Stage I checkpoint 55.7% success on sequence length | Improved |
| time series specialization training (SFT+RL) | TimeOmni-1 · DROP, GPQA, ReClor average | accuracy: +16.5% over base, +1.3% over Stage 1 | Improved |
| multi-task joint training for ANS-SFT on causality discovery (ablation) | ANS-SFT · Causality Discovery (ID) | accuracy: 35.7 -> 30.5 | Hurt |
Later papers that compared with this method
2 later accepted papers report TimeOmni-1 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning (ICML 2026 · better on 1 of 1 shared result)
- TimeOmni-VL: Unified Models for Time Series Understanding and Generation (ICML 2026 · better on 0 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
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop (NeurIPS 2025 · similarity 0.90)
- Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting (NeurIPS 2026 · similarity 0.89)
- Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis (NeurIPS 2024 · similarity 0.89)
- STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis (AAAI 2025 · similarity 0.89)
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024 · similarity 0.88)
- TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents (AAAI 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.
