الملخص
Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-based temporal reasoning. Yet current time-series foundation models remain fragmented across these capabilities: numerical specialists often provide the strongest forecasts, while language-based models offer broader contextual understanding and analysis. A central challenge is to unify these heterogeneous capabilities without reducing their individual performance. We introduce OpenTSLM TeeMoE, a generalist time-series language model that can forecast directly from observed time series, reason over textual context and temporal patterns, and synthesize and refine predictions from external numerical forecasting specialists. We independently train three low-rank experts for forecast aggregation, native forecasting, and temporal analysis over a shared backbone. A learned LoRA mixture-of-experts controller then weights their frozen parameter updates for each request. Our proposed model achieves strong performance on widely used benchmarks for time series forecasting, context-conditioned prediction, and language-based temporal reasoning, ranking among the top three on GIFT-Eval by mean MASE rank, Context is Key by RCRPS, and TimeSeriesExam by accuracy.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Chen, T., Stoffregen, T., Xu, M., Kaar, T., Maritsch, M., Pompei, G., Zumarraga, N., Jakob, R., Schmiedmayer, P., Langer, P., & Liu, J. (2026). OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning. https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning
MLA 9
Chen, Tony, et al. "OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning." https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning.
شيكاغو (المؤلف–التاريخ)
Chen, Tony, Timo Stoffregen, Maxwell Xu, Thomas Kaar, Martin Maritsch, Geremia Pompei, Nicolas Zumarraga, Robert Jakob, Paul Schmiedmayer, Patrick Langer, and Juncheng Liu. 2026. "OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning." https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning.
هارفارد
Chen, T., Stoffregen, T., Xu, M., Kaar, T., Maritsch, M., Pompei, G., Zumarraga, N., Jakob, R., Schmiedmayer, P., Langer, P. and Liu, J. (2026) 'OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning', Available at: https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning.
فانكوفر
Chen T, Stoffregen T, Xu M, Kaar T, Maritsch M, Pompei G, et al. OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning. https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning
IEEE
T. Chen, T. Stoffregen, M. Xu, T. Kaar, M. Maritsch, G. Pompei, N. Zumarraga, R. Jakob, P. Schmiedmayer, P. Langer, and J. Liu, "OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning," https://omanscience.com/ar/articles/opentslm-teemoe-a-unified-time-series-language-model-for-forecasting-contextual-prediction-and-reasoning.