User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms. Despite its importance, conventional continuous embedding methods face significant challenges, including the lack of a unified paradigm for multi-source data integration, prohibitive storage overhead due to low information density, and the lack of multi-scale modeling granularity. To overcome these limitations, we introduce FOUNDv2, a comprehensive user representation scheme centered on the Unified User Quantized Tokenizer U2QT) framework. FOUNDv2 transforms heterogeneous user data into a standardized discrete token space through a robust two-stage architecture. Specifically, the framework first extracts compact feature representations and subsequently employs a multi-view RQ-VAE to discretize them into storage-efficient tokens using shared and source-specific codebooks. To empower these representations with predictive intelligence, we further design multi-scale alignment objectives to capture both fine-grained behavioral dependencies and macro-temporal periodicity. Extensive experiments on various benchmarks demonstrate that FOUNDv2 consistently outperforms task-specific baselines while achieving substantial reductions in storage and computational costs. Finally, the large-scale deployment of FOUNDv2 on Alipay validates its practical scalability and efficiency across diverse industrial scenarios. The main code is available at: https://github.com/chuanhe1999/FOUNDv2.

翻译：用户表示学习是大规模网络平台个性化服务的基础支柱。尽管其重要性不言而喻，传统的连续嵌入方法仍面临重大挑战，包括缺乏用于多源数据融合的统一范式、因信息密度低导致的过高存储开销，以及缺乏多尺度建模粒度。为克服这些限制，我们提出了FOUNDv2，这是一个以统一用户量化分词器（Unified User Quantized Tokenizer, U2QT）框架为核心的综合用户表示方案。FOUNDv2通过一种稳健的两阶段架构，将异构用户数据转化为标准化的离散分词空间。具体而言，该框架首先提取紧凑的特征表示，随后采用多视角残差量化变分自编码器（Multi-view RQ-VAE），利用共享和源特定码本将其离散化为存储高效的离散化码。为赋予这些表示预测智能，我们进一步设计了多尺度对齐目标，以捕捉细粒度的行为依赖性和宏观时间周期性。在各种基准测试上的广泛实验表明，FOUNDv2在实现存储和计算成本大幅降低的同时，始终优于任务特定基线。最后，FOUNDv2在支付宝上的大规模部署验证了其在多样化工业场景中的实用可扩展性和效率。主要代码可在 https://github.com/chuanhe1999/FOUNDv2 获取。