OneMall: One Architecture, More Scenarios — End-to-End Generative Recommender Family for E-commerce
Open Access
- 6 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8768-8775
Abstract
In the wave of generative recommendation, we present OneMall, an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou. Our OneMall systematically unifies the e-commerce's multiple item distribution scenarios, such as Product-card, short-video and live-streaming. Specifically, it comprises three key components, aligning the entire model training pipeline to the LLM's pre-training/post-training: (1)E-commerce Semantic Tokenizer : we provide a tokenizer solution that captures both real-world semantics and business-specific item relations across different scenarios; (2)Transformer-based Architecture : we largely utilize Transformer as our model backbone, e.g., employing Query-Former for long sequence compression, Cross-Attention for multi-behavior sequence fusion, and Sparse MoE for scalable auto-regressive generation; (3)Reinforcement Learning Pipeline: we further connect retrieval and ranking models via RL, enabling the ranking model to serve as a reward signal for end-to-end policy retrieval model optimization. Extensive experiments demonstrate that OneMall achieves consistent improvements across all e-commerce scenarios: +14.7% GMV in Product-Card, +10.3% GMV in Short-Video, and +4.9% GMV in Live-Streaming. OneMall has been deployed, serving over 400 million daily active users at Kuaishou.Keywords
This publication has 14 references indexed in Scilit:
- LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders2025
- TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou2023
- Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction2020
- Controllable Multi-Interest Framework for Recommendation2020
- Multi-Interest Network with Dynamic Routing for Recommendation at Tmall2019
- Sampling-bias-corrected neural modeling for large corpus item recommendations2019
- Self-Attentive Sequential Recommendation2018
- Deep Interest Network for Click-Through Rate Prediction2018
- Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts2018
- Deep Neural Networks for YouTube Recommendations2016