AI RESEARCH
A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
arXiv CS.LG
•
ArXi:2603.22586v1 Announce Type: new In-context learning (ICL) allows a model to adapt at inference time by conditioning on examples rather than updating parameters. Existing time-series foundation models use implicit positional context, retrieval, or task-specific objectives, but rarely explicit instruction-conditioned nstrations. We present a foundation model for instruction-conditioned in-context time-series tasks based on a quantile-regression T5 encoder-decoder.