OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning

Name: OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning
Uploaded: 2026-10-19T08:49:40.659182+00:00
Duration: 485 s
Description: OpenTSLM TeeMoE is a generalist time-series language model that combines numerical forecasting, context-conditioned prediction, and temporal reasoning into one system. It achieves this by using a shared backbone and three independently trained low-rank experts, managed by a learned controller that routes requests to the right specialist for optimal performance across various benchmarks.

OpenTSLM TeeMoE is a generalist time-series language model that combines numerical forecasting, context-conditioned prediction, and temporal reasoning into one system. It achieves this by using a shared backbone and three independently trained low-rank experts, managed by a learned controller that routes requests to the right specialist for optimal performance across various benchmarks.

Open the full episode