# MTGR: Industrial-Scale Generative Recommendation Framework in Meituan

arXiv: https://arxiv.org/abs/2505.18654 · HTML: https://mlsanity.com/paper/2505.18654/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2025.

## Built on by (most cited first, 30 of 49)

- [CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation](https://mlsanity.com/paper/2511.22707/) (2025)
- [MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation](https://mlsanity.com/paper/2508.15281/) (2025)
- [Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design](https://mlsanity.com/paper/2602.10016/) (2026)
- [Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale](https://mlsanity.com/paper/2603.00632/) (2026)
- [Request-Only Optimization for Recommendation Systems](https://mlsanity.com/paper/2508.05640/) (2025)
- [CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation](https://mlsanity.com/paper/2604.05113/) (2026)
- [GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation](https://mlsanity.com/paper/2604.14878/) (2026)
- [Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment](https://mlsanity.com/paper/2508.02929/) (2025)
- [xLLM Technical Report](https://mlsanity.com/paper/2510.14686/) (2025)
- [End-to-End Semantic ID Generation for Generative Advertisement Recommendation](https://mlsanity.com/paper/2602.10445/) (2026)
- [DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion](https://mlsanity.com/paper/2508.14500/) (2025)
- [SynerGen: Contextualized Generative Recommender for Unified Search and Recommendation](https://mlsanity.com/paper/2509.21777/) (2025)
- [xGR: Efficient Generative Recommendation Serving at Scale](https://mlsanity.com/paper/2512.11529/) (2025)
- [RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference](https://mlsanity.com/paper/2601.01712/) (2026)
- [Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation](https://mlsanity.com/paper/2602.11799/) (2026)
- [Beyond Interleaving: Causal Attention Reformulations for Generative Recommender Systems](https://mlsanity.com/paper/2603.10369/) (2026)
- [Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation](https://mlsanity.com/paper/2604.02324/) (2026)
- [MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches](https://mlsanity.com/paper/2604.22881/) (2026)
- [LLMs Need Encoders for Semantic IDs Too](https://mlsanity.com/paper/2606.00324/) (2026)
- [TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation](https://mlsanity.com/paper/2606.07688/) (2026)
- [Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation](https://mlsanity.com/paper/2510.05125/) (2025)
- [HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent](https://mlsanity.com/paper/2512.24787/) (2025)
- [UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization](https://mlsanity.com/paper/2601.17438/) (2026)
- [LocalSUG: City-Preference-Enhanced LLM for Query Suggestion in Local-Life Services](https://mlsanity.com/paper/2603.04946/) (2026)
- [UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale](https://mlsanity.com/paper/2606.00422/) (2026)
- [Selection and Exploitation of High-Quality Knowledge from Large Language Models for Recommendation](https://mlsanity.com/paper/2508.07223/) (2025)
- [DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou](https://mlsanity.com/paper/2508.17754/) (2025)
- [Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Prediction](https://mlsanity.com/paper/2509.19876/) (2025)
- [MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths](https://mlsanity.com/paper/2510.08932/) (2025)
- [Cross-Scenario Unified Modeling of User Interests at Billion Scale](https://mlsanity.com/paper/2510.14788/) (2025)

## Abstract (arXiv)

Scaling law has been extensively validated in many domains such as natural language processing and computer vision. In the recommendation system, recent work has adopted generative recommendations to achieve scalability, but their generative approaches require abandoning the carefully constructed cross features of traditional recommendation models. We found that this approach significantly degrades model performance, and scaling up cannot compensate for it at all. In this paper, we propose MTGR (Meituan Generative Recommendation) to address this issue. MTGR is modeling based on the HSTU architecture and can retain the original deep learning recommendation model (DLRM) features, including cross features. Additionally, MTGR achieves training and inference acceleration through user-level compression to ensure efficient scaling. We also propose Group-Layer Normalization (GLN) to enhance the performance of encoding within different semantic spaces and the dynamic masking strategy to avoid information leakage. We further optimize the training frameworks, enabling support for our models with 10 to 100 times computational complexity compared to the DLRM, without significant cost increases. MTGR achieved 65x FLOPs for single-sample forward inference compared to the DLRM model, resulting in the largest gain in nearly two years both offline and online. This breakthrough was successfully deployed on Meituan, the world's largest food delivery platform, where it has been handling the main traffic.