OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Kun, Zhang, Jingming, Cheng, Wei, Cheng, Yansong, Zhang, Jiaqi, Lu, Hao, Zhang, Xu, Gan, Haixiang, Cao, Jiangxia, Wang, Tenglong, Zhang, Ximing, Xia, Boyang, Cai, Kuo, Wang, Shiyao, Dou, Hongjian, Yu, Jinkai, Wen, Mingxing, Luo, Qiang, Liang, Dongxu, Lei, Chenyi, Wang, Jun, Liu, Runan, Liu, Zhaojie, Tang, Ruiming, Gao, Tingting, Liu, Shaoguo, Ding, Yuqing, Kong, Hui, Li, Han, Zhou, Guorui, Ou, Wenwu, Gai, Kun
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915768313053184
author Zhang, Kun
Zhang, Jingming
Cheng, Wei
Cheng, Yansong
Zhang, Jiaqi
Lu, Hao
Zhang, Xu
Gan, Haixiang
Cao, Jiangxia
Wang, Tenglong
Zhang, Ximing
Xia, Boyang
Cai, Kuo
Wang, Shiyao
Dou, Hongjian
Yu, Jinkai
Wen, Mingxing
Luo, Qiang
Liang, Dongxu
Lei, Chenyi
Wang, Jun
Liu, Runan
Liu, Zhaojie
Tang, Ruiming
Gao, Tingting
Liu, Shaoguo
Ding, Yuqing
Kong, Hui
Li, Han
Zhou, Guorui
Ou, Wenwu
Gai, Kun
author_facet Zhang, Kun
Zhang, Jingming
Cheng, Wei
Cheng, Yansong
Zhang, Jiaqi
Lu, Hao
Zhang, Xu
Gan, Haixiang
Cao, Jiangxia
Wang, Tenglong
Zhang, Ximing
Xia, Boyang
Cai, Kuo
Wang, Shiyao
Dou, Hongjian
Yu, Jinkai
Wen, Mingxing
Luo, Qiang
Liang, Dongxu
Lei, Chenyi
Wang, Jun
Liu, Runan
Liu, Zhaojie
Tang, Ruiming
Gao, Tingting
Liu, Shaoguo
Ding, Yuqing
Kong, Hui
Li, Han
Zhou, Guorui
Ou, Wenwu
Gai, Kun
contents 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: +13.01\% GMV in product-card, +15.32\% Orders in Short-Video, and +2.78\% Orders in Live-Streaming. OneMall has been deployed, serving over 400 million daily active users at Kuaishou.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce
Zhang, Kun
Zhang, Jingming
Cheng, Wei
Cheng, Yansong
Zhang, Jiaqi
Lu, Hao
Zhang, Xu
Gan, Haixiang
Cao, Jiangxia
Wang, Tenglong
Zhang, Ximing
Xia, Boyang
Cai, Kuo
Wang, Shiyao
Dou, Hongjian
Yu, Jinkai
Wen, Mingxing
Luo, Qiang
Liang, Dongxu
Lei, Chenyi
Wang, Jun
Liu, Runan
Liu, Zhaojie
Tang, Ruiming
Gao, Tingting
Liu, Shaoguo
Ding, Yuqing
Kong, Hui
Li, Han
Zhou, Guorui
Ou, Wenwu
Gai, Kun
Information Retrieval
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: +13.01\% GMV in product-card, +15.32\% Orders in Short-Video, and +2.78\% Orders in Live-Streaming. OneMall has been deployed, serving over 400 million daily active users at Kuaishou.
title OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce
topic Information Retrieval
url https://arxiv.org/abs/2601.21770