Tempo extends language models to understand time series data

TEMPO: Time Series Understanding via Discrete Tokenization

Computation and Language

Summary

Interpreting time series data, like activity or sleep patterns, is tricky because it mixes numbers and words. The authors developed TEMPO, which turns chunks of time series data into special codes that a language model can understand alongside text. This approach helps the model make sense of both signals and written context together. They tested TEMPO on tasks like recognizing activities and diagnosing faults, showing it works well.

What this means in practice

  • For industrial maintenance teams: Use integrated signal and text analysis to improve early detection of bearing faults and reduce machinery downtime.$Commercial implications: Offers a diagnostic tool combining sensor data with textual context, enhancing predictive maintenance products for manufacturing companies.
  • For healthcare monitoring teams: Combine vital sign recordings with patient notes for automated sleep staging to improve patient monitoring workflows.

Authors

Riccardo Maggioni

Abstract

Time-series interpretation often requires both numerical observations and textual context. Integrating these inputs into a pretrained language model raises a representation question: how should a signal enter the model's token sequence? We present TEMPO, which extends an LLM's vocabulary with discrete codes from a context-aware Transformer tokenizer using finite scalar quantization. A frozen tokenizer maps four-step patches to a 625-code vocabulary; signal tokens, scale statistics, and text are then processed by the LLM's existing self-attention layers. Adaptation updates the new token embeddings and DoRA adapters. With a Qwen3-4B backbone and task-specific fine-tuning, TEMPO achieves macro-F1 scores of 89.0% on activity recognition, 85.0% on sleep staging, and 86.0% on bearing-fault diagnosis. Time-series question answering and qualitative bearing-diagnosis examples further illustrate how this interface combines signal representations with textual context. Together, these results demonstrate the utility of discrete vocabulary extension for time-series understanding.