SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Wei, Guo, Xingyu, Li, Shuang, Zhang, Fuwei, Yuan, Meng, Fan, Jing, Zhang, Zhao, Wang, Deqing, Zhuang, Fuzhen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909055005491200
author Chen, Wei
Guo, Xingyu
Li, Shuang
Zhang, Fuwei
Yuan, Meng
Fan, Jing
Zhang, Zhao
Wang, Deqing
Zhuang, Fuzhen
author_facet Chen, Wei
Guo, Xingyu
Li, Shuang
Zhang, Fuwei
Yuan, Meng
Fan, Jing
Zhang, Zhao
Wang, Deqing
Zhuang, Fuzhen
contents Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studies have incorporated multimodal signals to provide richer token-level evidence for generation. However, existing approaches largely rely on alignment-centric fusion and underexplore synergistic information across modalities. In practice, synergistic information plays a critical role in capturing emergent item properties that cannot be inferred from any single modality alone. Such properties encode intrinsic item semantics and guide user preferences, enabling models to move beyond surface-level feature matching. To address this limitation, we propose \textbf{SynGR}, a synergistic generative recommendation framework that explicitly encourages the exploitation of cross-modal dependencies during generation. By constraining overreliance on dominant modalities, SynGR enables the model to capture emergent item semantics beyond shared or modality-specific signals. Extensive experiments across three benchmark datasets demonstrate that SynGR achieves superior performance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18920
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
Chen, Wei
Guo, Xingyu
Li, Shuang
Zhang, Fuwei
Yuan, Meng
Fan, Jing
Zhang, Zhao
Wang, Deqing
Zhuang, Fuzhen
Information Retrieval
Artificial Intelligence
Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studies have incorporated multimodal signals to provide richer token-level evidence for generation. However, existing approaches largely rely on alignment-centric fusion and underexplore synergistic information across modalities. In practice, synergistic information plays a critical role in capturing emergent item properties that cannot be inferred from any single modality alone. Such properties encode intrinsic item semantics and guide user preferences, enabling models to move beyond surface-level feature matching. To address this limitation, we propose \textbf{SynGR}, a synergistic generative recommendation framework that explicitly encourages the exploitation of cross-modal dependencies during generation. By constraining overreliance on dominant modalities, SynGR enables the model to capture emergent item semantics beyond shared or modality-specific signals. Extensive experiments across three benchmark datasets demonstrate that SynGR achieves superior performance.
title SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2605.18920