QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models

On GIFT-Eval, quantile alignment reduces average member MASE and CRPS by 7.4% and 9.8%. It comes from a paper posted to arXiv on 2 November 2026. Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this variability, yet zero-shot deployment provides no target labels for selecting or weighting them. We find that a model pool is useful not only as a final ensemble, but also as a probability reference for transforming each member forecast. Aligning quantiles through this pool-relative reference improves every member forecast in aggregate. Motivated by this finding, we propose QUAL (Quantile alignment), a simple label-free framework for improving and combining diverse TSFMs. QUAL first produces aligned member forecasts, then applies Huber aggregation and rearrangement to obtain a robust combined forecast without training or model modification. The full framework remains robust when weak forecasters enter a candidate pool whose quality cannot be verified in advance. Code is available at https://github.com/junhyeokkang/QUAL.

Why it counts

On GIFT-Eval, quantile alignment reduces average member MASE and CRPS by 7.4% and 9.8%. Aligning quantiles through this pool-relative reference improves every member forecast in aggregate. QUAL first produces aligned member forecasts, then applies Huber aggregation and rearrangement to obtain a robust combined forecast without training or model modification.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.