发表机构
TikTok-Data-Content Intelligence & TikTok-Data-Feed Quality（TikTok数据内容智能与TikTok数据馈送质量）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
X-Rec通过流匹配在连续嵌入空间学习推荐分布，结合锚定条件、黎曼流匹配和后期交互扩散Transformer，实现高效检索，显著优于U2I并匹配SID-AR质量，吞吐量提升3.46倍，已在TikTok部署并提升参与度。
AI 中文摘要
生成建模的最新进展通过将推荐问题表述为下一项生成问题，重塑了推荐系统。现有的检索方法主要遵循两种范式：用户到项目（U2I）方法使用一个或几个确定性嵌入来表示用户上下文，这限制了捕捉多样化和多模式兴趣的能力；而基于语义ID的自回归（SID-AR）方法则建模更具表达力的分布，但遭受量化误差和顺序解码低吞吐量的困扰。为了解决这些局限性，我们提出了X-Rec，通过流匹配直接在连续项目嵌入空间中学习推荐分布，并生成嵌入触发器以用于近似最近邻检索。X-Rec包含三个关键设计，使这种表述有效且高效。首先，我们引入锚定条件，将生成过程分解为粗略语义区域选择和细粒度细化。其次，我们采用黎曼流匹配，使生成轨迹与项目嵌入的超球面几何对齐。第三，我们设计了一个后期交互扩散Transformer，将重复的向量场估计限制在最后的Transformer层。在流式基准测试上，X-Rec显著优于U2I基线，匹配SID-AR方法的检索质量，并提供比SID-AR高3.46倍的推理吞吐量。X-Rec还已被部署为TikTok上特定垂直内容的新检索源，其中连续两次上线在垂直参与度（+4.1484%）和总体参与度（+0.0111%）方面均取得了显著提升。
英文摘要
Recent advances in generative modeling have reshaped recommender systems by formulating recommendation as a next-item generation problem. Existing retrieval approaches primarily follow two paradigms: user-to-item (U2I) methods represent user context using one or a few deterministic embeddings, which limits the ability to capture diverse and multi-mode interests, while semantic-ID-based autoregressive (SID-AR) methods model more expressive distributions but suffer from quantization errors and the low throughput of sequential decoding. To address these limitations, we propose X-Rec to directly learn the recommendation distribution in the continuous item embedding space through flow matching and generate embedding triggers for approximate nearest neighbor retrieval. X-Rec incorporates three key designs to make this formulation effective and efficient. First, we introduce anchor conditioning to decompose generation into coarse semantic-region selection and fine-grained refinement. Second, we adopt Riemannian flow matching to align generative trajectories with the hyperspherical geometry of item embeddings. Third, we design a late-interaction diffusion Transformer that restricts repeated velocity-field estimation to the final Transformer layer. On a streaming benchmark, X-Rec substantially outperforms U2I baselines, matches the retrieval quality of SID-AR methods, and delivers 3.46x higher inference throughput than SID-AR. X-Rec has also been deployed as a new retrieval source for a specific vertical content on TikTok, where two consecutive launches have yielded significant improvements in both vertical engagement (+4.1484%) and general engagement (+0.0111%).
