In large-scale industrial recommendation systems, retrieval must produce high-quality candidates from massive corpora under strict latency. Recently, Generative Retrieval (GR) has emerged as a viable alternative to Embedding-Based Retrieval (EBR), which quantizes items into a finite token space and decodes candidates autoregressively, providing a scalable path that explicitly models target-history interactions via cross-attention. However, three challenges persist: 1) how to balance users' long-term and short-term interests , 2) noise interference when generating hierarchical semantic IDs (SIDs), 3) the absence of explicit modeling for negative feedback such as exposed items without clicks. To address these challenges, we propose DualGR, a generative retrieval framework that explicitly models dual horizons of user interests with selective activation. Specifically, DualGR utilizes Dual-Branch Long/Short-Term Router (DBR) to cover both stable preferences and transient intents by explicitly modeling users' long- and short-term behaviors. Meanwhile, Search-based SID Decoding (S2D) is presented to control context-induced noise and enhance computational efficiency by constraining candidate interactions to the current coarse (level-1) bucket during fine-grained (level-2/3) SID prediction. % also reinforcing intra-class consistency. Finally, we propose an Exposure-aware Next-Token Prediction Loss (ENTP-Loss) that treats "exposed-but-unclicked" items as hard negatives at level-1, enabling timely interest fade-out. On the large-scale Kuaishou short-video recommendation system, DualGR has achieved outstanding performance. Online A/B testing shows +0.527% video views and +0.432% watch time lifts, validating DualGR as a practical and effective paradigm for industrial generative retrieval.

翻译：在大规模工业推荐系统中，检索必须在严格延迟约束下从海量语料库中生成高质量候选。近年来，生成式检索（Generative Retrieval, GR）已成为基于嵌入的检索（Embedding-Based Retrieval, EBR）的一种可行替代方案，其将物品量化到有限令牌空间并通过自回归方式解码候选，提供了一条可扩展的路径，通过交叉注意力显式建模目标-历史交互。然而，三个挑战依然存在：1）如何平衡用户的长期与短期兴趣，2）生成分层语义ID（Semantic IDs, SIDs）时的噪声干扰，3）对负面反馈（如曝光未点击物品）缺乏显式建模。为应对这些挑战，我们提出DualGR，一种通过选择性激活显式建模用户兴趣双重视野的生成式检索框架。具体而言，DualGR利用双分支长/短期路由器（Dual-Branch Long/Short-Term Router, DBR），通过显式建模用户的长期与短期行为，覆盖稳定偏好与瞬时意图。同时，我们提出基于搜索的SID解码（Search-based SID Decoding, S2D），通过将细粒度（level-2/3）SID预测期间的候选交互约束在当前粗粒度（level-1）桶内，以控制上下文诱导噪声并提升计算效率。最后，我们提出曝光感知的下一个令牌预测损失（Exposure-aware Next-Token Prediction Loss, ENTP-Loss），将“曝光未点击”物品视为level-1的硬负样本，实现兴趣的及时衰减。在大规模快手短视频推荐系统中，DualGR取得了优异性能。在线A/B测试显示视频播放量提升+0.527%，观看时长提升+0.432%，验证了DualGR作为工业生成式检索的实用且有效的范式。