Saved in:
Bibliographic Details
Main Authors: Song, Xin, Guan, Zhilin, Han, Ruidong, Tang, Binghao, Chen, Tianwen, Li, Bing, Li, Zihao, Zhang, Han, Jiang, Fei, Wang, Qing, Xu, Zikang, Li, Fengyi, Jing, Chunzhen, Yu, Lei, Lin, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11235
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911444302299136
author Song, Xin
Guan, Zhilin
Han, Ruidong
Tang, Binghao
Chen, Tianwen
Li, Bing
Li, Zihao
Zhang, Han
Jiang, Fei
Wang, Qing
Xu, Zikang
Li, Fengyi
Jing, Chunzhen
Yu, Lei
Lin, Wei
author_facet Song, Xin
Guan, Zhilin
Han, Ruidong
Tang, Binghao
Chen, Tianwen
Li, Bing
Li, Zihao
Zhang, Han
Jiang, Fei
Wang, Qing
Xu, Zikang
Li, Fengyi
Jing, Chunzhen
Yu, Lei
Lin, Wei
contents Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We propose MTFM (Meituan Foundation Model for Recommendation), a transformer-based framework that addresses these challenges. Instead of pre-aligning inputs, MTFM transforms cross-domain data into heterogeneous tokens, capturing multi-scenario knowledge in an alignment-free manner. To enhance efficiency, we first introduce a multi-scenario user-level sample aggregation that significantly enhances training throughput by reducing the total number of instances. We further integrate Grouped-Query Attention and a customized Hybrid Target Attention to minimize memory usage and computational complexity. Furthermore, we implement various system-level optimizations, such as kernel fusion and the elimination of CPU-GPU blocking, to further enhance both training and inference throughput. Offline and online experiments validate the effectiveness of MTFM, demonstrating that significant performance gains are achieved by scaling both model capacity and multi-scenario training data.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11235
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan
Song, Xin
Guan, Zhilin
Han, Ruidong
Tang, Binghao
Chen, Tianwen
Li, Bing
Li, Zihao
Zhang, Han
Jiang, Fei
Wang, Qing
Xu, Zikang
Li, Fengyi
Jing, Chunzhen
Yu, Lei
Lin, Wei
Information Retrieval
Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We propose MTFM (Meituan Foundation Model for Recommendation), a transformer-based framework that addresses these challenges. Instead of pre-aligning inputs, MTFM transforms cross-domain data into heterogeneous tokens, capturing multi-scenario knowledge in an alignment-free manner. To enhance efficiency, we first introduce a multi-scenario user-level sample aggregation that significantly enhances training throughput by reducing the total number of instances. We further integrate Grouped-Query Attention and a customized Hybrid Target Attention to minimize memory usage and computational complexity. Furthermore, we implement various system-level optimizations, such as kernel fusion and the elimination of CPU-GPU blocking, to further enhance both training and inference throughput. Offline and online experiments validate the effectiveness of MTFM, demonstrating that significant performance gains are achieved by scaling both model capacity and multi-scenario training data.
title MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan
topic Information Retrieval
url https://arxiv.org/abs/2602.11235