Skip to content

Multimodal Irregular Time Series Language Model (MILM)

Home / Concepts / Multimodal Irregular Time Series Language Model (MILM)

Multimodal Irregular Time Series Language Model (MILM)

Auto-generated stub. Edit this file to add more details.

A framework that represents multimodal irregular time series as time-ordered XML triplets and employs a two-stage LLM training strategy to capture both sampling patterns and numerical/textual values.

Why It Matters

Central novel framework for handling multimodal irregular time series data by leveraging LLMs through a structured XML-based triplet representation.

Evidence

MILM (Multimodal Irregular time series Language Model), which represents MITS as time-ordered triplets in Extensible Markup Language (XML) format and fine-tunes an LLM through a two-stage strategy for MITS classification.

Metadata & Links