@inproceedings{huang-etal-2025-cross-moe,
title = "Cross-{M}o{E}: An Efficient Temporal Prediction Framework Integrating Textual Modality",
author = "Huang, Ruizheng and
Zhang, Zhicheng and
Wang, Yong",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1520/",
pages = "29915--29926",
ISBN = "979-8-89176-332-6",
abstract = "It has been demonstrated that incorporating external information as textual modality can effectively improve time series forecasting accuracy. However, current multi-modal models ignore the dynamic and different relations between time series patterns and textual features, which leads to poor performance in temporal-textual feature fusion. In this paper, we propose a lightweight and model-agnostic temporal-textual fusion framework named Cross-MoE. It replaces Cross Attention with Cross-Ranker to reduce computational complexity, and enhances modality-aware correlation memorization with Mixture-of-Experts (MoE) networks to tolerate the distributional shifts in time series. The experimental results demonstrate a 8.78{\%} average reduction in Mean Squared Error (MSE) compared to the SOTA multi-modal time series framework. Notably, our method requires only 75{\%} of computational overhead and 12.5{\%} of activated parameters compared with Cross Attention mechanism. Our codes are available at \url{https://github.com/Kilosigh/Cross-MoE.git}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-cross-moe">
<titleInfo>
<title>Cross-MoE: An Efficient Temporal Prediction Framework Integrating Textual Modality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruizheng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>It has been demonstrated that incorporating external information as textual modality can effectively improve time series forecasting accuracy. However, current multi-modal models ignore the dynamic and different relations between time series patterns and textual features, which leads to poor performance in temporal-textual feature fusion. In this paper, we propose a lightweight and model-agnostic temporal-textual fusion framework named Cross-MoE. It replaces Cross Attention with Cross-Ranker to reduce computational complexity, and enhances modality-aware correlation memorization with Mixture-of-Experts (MoE) networks to tolerate the distributional shifts in time series. The experimental results demonstrate a 8.78% average reduction in Mean Squared Error (MSE) compared to the SOTA multi-modal time series framework. Notably, our method requires only 75% of computational overhead and 12.5% of activated parameters compared with Cross Attention mechanism. Our codes are available at https://github.com/Kilosigh/Cross-MoE.git</abstract>
<identifier type="citekey">huang-etal-2025-cross-moe</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1520/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>29915</start>
<end>29926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-MoE: An Efficient Temporal Prediction Framework Integrating Textual Modality
%A Huang, Ruizheng
%A Zhang, Zhicheng
%A Wang, Yong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F huang-etal-2025-cross-moe
%X It has been demonstrated that incorporating external information as textual modality can effectively improve time series forecasting accuracy. However, current multi-modal models ignore the dynamic and different relations between time series patterns and textual features, which leads to poor performance in temporal-textual feature fusion. In this paper, we propose a lightweight and model-agnostic temporal-textual fusion framework named Cross-MoE. It replaces Cross Attention with Cross-Ranker to reduce computational complexity, and enhances modality-aware correlation memorization with Mixture-of-Experts (MoE) networks to tolerate the distributional shifts in time series. The experimental results demonstrate a 8.78% average reduction in Mean Squared Error (MSE) compared to the SOTA multi-modal time series framework. Notably, our method requires only 75% of computational overhead and 12.5% of activated parameters compared with Cross Attention mechanism. Our codes are available at https://github.com/Kilosigh/Cross-MoE.git
%U https://aclanthology.org/2025.emnlp-main.1520/
%P 29915-29926
Markdown (Informal)
[Cross-MoE: An Efficient Temporal Prediction Framework Integrating Textual Modality](https://aclanthology.org/2025.emnlp-main.1520/) (Huang et al., EMNLP 2025)
ACL