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.

翻译：生成式推荐（Generative Recommendation, GR）通过将项目推荐建模为基于项目标识符的序列到序列生成任务，已成为一种前景广阔的研究范式。近期研究引入多模态信号，为生成过程提供了更丰富的词元级证据。然而，现有方法主要依赖于以对齐为中心的融合方式，对跨模态的协同信息探索不足。在实际应用中，协同信息对于捕捉无法从单一模态推断出的项目涌现属性至关重要。此类属性编码了项目的内在语义，并引导用户偏好，使模型能够超越浅层特征匹配。为解决这一局限，我们提出\textbf{SynGR}——一种协同生成式推荐框架，其明确鼓励在生成过程中利用跨模态依赖性。通过约束对主导模态的过度依赖，SynGR使模型能够捕捉超越共享或模态特异性信号的涌现项目语义。在三个基准数据集上的大量实验表明，SynGR实现了优越的性能。