---
title: "QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41100v1"
permalink: "https://feed.astralor.com/items/itm_0f1e652424ee70468dd47943"
published: "2026-10-30T00:41:39.000Z"
score: 53
channel: "tech"
tags: ["安全","RAG","QUAL","Quantile Alignment Improves","Zero-Shot Time-Series Foundation","Models Time-series","TSFMs","Combining"]
---

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

## 速览

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 …

## 关键点

- 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.

## 全文

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. On GIFT-Eval, quantile alignment reduces average member MASE and CRPS by 7.4% and 9.8%. 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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_0f1e652424ee70468dd47943