Saved in:
Bibliographic Details
Main Authors: Liu, Yiding, Hu, Yifan, Xia, Hongjie, Liu, Peiyuan, Chen, Hongzhou, Dai, Xilin, Dong, Zewei, Yang, Jiang-Ming
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.27286
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918524794961920
author Liu, Yiding
Hu, Yifan
Xia, Hongjie
Liu, Peiyuan
Chen, Hongzhou
Dai, Xilin
Dong, Zewei
Yang, Jiang-Ming
author_facet Liu, Yiding
Hu, Yifan
Xia, Hongjie
Liu, Peiyuan
Chen, Hongzhou
Dai, Xilin
Dong, Zewei
Yang, Jiang-Ming
contents Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing TSFMs remain univariate, and recent efforts to enable cross-variate modeling still operate directly within the raw variate space. This design introduces fundamental limitations in semantic alignment and relational expressivity. Specifically, raw-space group mixing lacks a dedicated mechanism to align heterogeneous physical quantities, while standard non-negative attention fails to capture the complex synergistic and antagonistic interactions ubiquitous in real-world systems. To address these challenges, we propose Falcon-X, decouples variates from the raw space and maps them into a unified latent prototype space. Falcon-X employs a Unified Prototype Diff-Attention mechanism that explicitly evaluates both positive and negative semantic affinities to explicitly align heterogeneous variates. Cross-variate interactions are then efficiently performed within this shared space via Latent Entity Attention, naturally facilitating zero-shot structural transfer. Finally, a Variate Reassembly Router robustly reconstructs variate-specific trajectories via a request-and-dispatch mechanism. Extensive evaluations on the GIFT-Eval and fev-bench benchmarks demonstrate that Falcon-X achieves state-of-the-art forecasting performance, offering a principled and scalable paradigm for complex multivariate environments. Falcon-X is publicly released to support future research.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27286
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
Liu, Yiding
Hu, Yifan
Xia, Hongjie
Liu, Peiyuan
Chen, Hongzhou
Dai, Xilin
Dong, Zewei
Yang, Jiang-Ming
Machine Learning
Artificial Intelligence
Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing TSFMs remain univariate, and recent efforts to enable cross-variate modeling still operate directly within the raw variate space. This design introduces fundamental limitations in semantic alignment and relational expressivity. Specifically, raw-space group mixing lacks a dedicated mechanism to align heterogeneous physical quantities, while standard non-negative attention fails to capture the complex synergistic and antagonistic interactions ubiquitous in real-world systems. To address these challenges, we propose Falcon-X, decouples variates from the raw space and maps them into a unified latent prototype space. Falcon-X employs a Unified Prototype Diff-Attention mechanism that explicitly evaluates both positive and negative semantic affinities to explicitly align heterogeneous variates. Cross-variate interactions are then efficiently performed within this shared space via Latent Entity Attention, naturally facilitating zero-shot structural transfer. Finally, a Variate Reassembly Router robustly reconstructs variate-specific trajectories via a request-and-dispatch mechanism. Extensive evaluations on the GIFT-Eval and fev-bench benchmarks demonstrate that Falcon-X achieves state-of-the-art forecasting performance, offering a principled and scalable paradigm for complex multivariate environments. Falcon-X is publicly released to support future research.
title Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.27286