Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS

Gaspard Berthelier; Mariia Baranova; Andrei-Tiberiu Pantea; Etienne Le Naour; Adrien Petralia; Tahar Nabil; Themis Palpanas

cs.LGMay 12, 2026

Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS

Authors: Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea, Etienne Le Naour, Adrien Petralia, Tahar Nabil, Themis Palpanas

Organizations: EDF R&D, Palaiseau · Inria Sophia-Antipolis, Université Côte d’Azur · Université Paris Cit'e

Abstract

Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings. Recent TSFM architectures, such as Chronos-2 and TabPFN-TS, aim to integrate covariates. In this paper, we design controlled experiments based on simple target-covariate relationships to assess this integration capability. Our results show that TabPFN-TS captures these relationships more effectively than Chronos-2, especially for short horizons, suggesting that the strong benchmark performance of Chronos-2 does not automatically translate into optimal modeling of simple covariate-target dependencies.

Explore similar work

CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting
Jun 9, 2026Yosuke Yamaguchi, Issei Suemitsu, Yuki Kajihara +1Zero-Shot Forecasting Time Series Foundation Models
TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model
Aug 4, 2026Gabriel da Costa Merlin, Diego Furtado SilvaTime-Series Classification Tabular Prior-Data Fitted Network
Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models
Sep 22, 2026Jinmyeong Choi, Jinkwan Jang, Seul Lee +1

Jun 9, 2026 · cs.LGJ/K move · Enter open · S save

CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting

Yosuke Yamaguchi, Issei Suemitsu, Yuki Kajihara, Wenpeng Wei

Research & Development Group, Hitachi Ltd., Tokyo, Japan

Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series. However, existing TSFMs often incur high computational cost and provide limited support for diverse variable types, often failing to account for covariates that exogenously influence target variability. To address these challenges, we propose CITRAS-FM, a tiny 7M-parameter TSFM that supports univariate, multivariate, and covariate-informed zero-shot forecasting with real-time CPU inference. Built on a patch-based, decoder-only Transformer, CITRAS-FM introduces Shifted Attention into the cross-variate module to effectively exploit known covariates accessible throughout the forecast horizon. Moreover, to enable covariate-aware pretraining despite the scarcity of covariate-rich corpora, we propose CovSynth, which synthesizes realistic covariates from decomposed components of target series. Experiments on fev-bench, spanning 100 tasks across various settings, demonstrate that CITRAS-FM achieves state-of-the-art zero-shot accuracy among sub-10M TSFMs while delivering sub-0.1-second CPU inference, offering a strong balance between forecasting accuracy and real-time deployability.

Zero-Shot Forecasting Time Series Foundation Models Snap-Fm

Open paper Ask about it PDF

Abstract

Explore similar work

CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting

TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model

Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models