ITGPT: Generative Pretraining on Irregular Timeseries

ArXi:2605.16069v1 Announce Type: new Timeseries regression models often struggle to leverage large volumes of labeled multimodal data, particularly when the data are irregularly sampled or contain missing values. This is common in domains like healthcare and predictive maintenance, where data are collected from unreliable sources, and labeling requires expert knowledge or costly equipments. Transformer-based large language models have proven effective on structured data such as text through self-supervised learning (SSL) and generative pre.