TimeOmni-o1: Bidirectionally Coupling Time Series Foundation Models and LLMs for Multimodal Reasoning and Forecasting
cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
Code: https://github.com/OpenTSLab/TimeOmni-o1
Project page: https://windowso.github.io/TimeOmni-o1-web
Terminology
Sources
- STRIDE: Reasoning-Aware Training for Time Series Forecasting
- Chronos-2: From Univariate to Universal Forecasting
- MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
- What If TSF: Reframing Time Series Forecasting as Scenario-Guided Multimodal Forecasting
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
- Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting
- Qwen3 Technical Report
- Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data