OneTrans-V2 is presented, one Transformer that unifies the entire cascade of retrieval, pre-rank, and fine-rank and introduces Decision-Conditioned Generative Retrieval (DCGR), which predicts a decision prefix describing the upcoming interaction and generates items conditioned on it, allowing business objectives to steer a single generative process.
Abstract
Industrial recommendation systems typically operate as a \emph{cascade} of retrieval, pre-rank, and fine-rank, but these stages are usually trained and served as separate models, causing repeated user-sequence encoding, isolated optimization, and duplicated engineering effort. Building on OneTrans'model-level unification, we present OneTrans-V2, one Transformer that unifies the entire cascade. It encodes the user behavior sequence once as a shared context while preserving stage-specific candidate features and computation. Joint training lets the three stages reinforce one another and enables in-model knowledge distillation from fine-rank to pre-rank. We scale the shared backbone with sparse mixture-of-experts (MoE), which increases capacity with bounded activated computation, and stabilize scaling with $\mu$P-style parameterization. To consolidate objective-specific retrieval channels, we introduce Decision-Conditioned Generative Retrieval (DCGR). DCGR predicts a decision prefix describing the upcoming interaction and generates items conditioned on it, allowing business objectives to steer a single generative process. Finally, Sequence-Native Training (SNT) organizes training around each user's lifelong behavior sequence and amortizes its encoding across exposures. Deployed across all three stages of a large-scale industrial recommendation system, OneTrans-V2 improves gross merchandise value (GMV) by 9.74\% and, with a co-designed serving stack, delivers $3.2\times$ the throughput of the cascade it replaces under the same hardware budget.
Industrial recommendation systems rely on multi-stage cascades whose retrieval, ranking, and serving components are difficult to replace jointly. We present GRP, a generative recommendation framework that combines retrieval, ranking, and reward modeling in a single encoder-decoder model, and evaluate a progressive path...
Wen-Feng Zhuo, Vincent Xue, Charles Wei et al.· arXiv.org· 0 citations
Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an interaction. We propose the Lifecycle-aware Interaction Factorization Transformer (LIFT), which decomposes each interaction into ordered Request, Item, Co...
Ke-Ji Miao, En-Hao Cheng, Yan Li et al.· 0 citations
Accurate product discovery on the Web requires recommendation models that rank catalog candidates within tight inference budgets. In semantic-ID recommendation, deployment can fuse code probabilities with item similarities, making the final ranking depend on their normalization and relative weights. This motivates a di...
Results show that UNIQUE provides a stable, efficient, and production-ready framework for unified retrieval and ranking in industrial recommendation, and a balanced quantization mechanism is further introduced to mitigate codebook imbalance and improve long-tail representation.
Zhuang-Chen-Ying-Ying Liu, Yong-Kang Fu, Zuo-Dong Yang et al.· Proceedings of the 20th ACM...· 0 citations
TGR (Tencent Generative Recommendation), an industrial framework that advances recommendation toward the generative paradigm along three coupled directions, is presented, which is deployed across Tencent production surfaces serving hundreds of millions of users.
T. Cheng, Hao-Nan Hu, Bei-Bei Kong et al.· 0 citations
Modeling lifetime user behavior sequences is essential for capturing long-range preferences in industrial recommendation, yet sequences containing up to 100K interactions make target-aware ranking prohibitively expensive. Search-based methods that retrieve from raw sequences incur candidate-dependent costs that grow wi...
Wen-Hao Li, Qing-Lin Jia, Cheng-Hou Jin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.