Awesome-Generative-Recommendation

🔍 Overview

This repository is a curated list of Awesome Generative Recommendation papers from recent years, with a primary focus on industry-level applications.

📚 Content

• Analyses
• Architecture
• Cross-Domain
• Diffusion-based
• LLM-based
• One Model
• Post Train
• Ranking
• Retrieval
• Semantic ID

---

Analyses

Survey papers, technical analyses, and perspective articles on generative recommendation

• How Well Does Generative Recommendation Generalize?, 2026.03,
• A Survey of Generative Recommendation from a Tri-Decoupled Perspective: Tokenization, Architecture, and Optimization, 2025.12,
• Understanding Generative Recommendation with Semantic IDs from a Model-scaling View, 2025.09,
• Generative Recommendation with Semantic IDs: A Practitioner's Handbook, 2025.07,
• GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models, 2025.07,

Architecture

Papers on model architectures, backbone design, and scaling for generative recommendation / sequence modeling

• SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching, 2026.09,
• SPARC: Sequence-aware Progressive Attribute Routing and Compression Framework for Generative Recommendation, 2026.07,
• SlimPer: Make Personalization Model Slim and Smart, 2026.07,
• UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence, 2026.05,
• MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders, 2026.02,
• Bending the Scaling Law Curve in Large-Scale Recommendation Systems, 2026.02,
• GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder, 2026.02,
• TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders, 2026.02,
• HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction, 2026.01,
• Make It Long, Keep It Fast: End-to-End 10k-Sequence Modeling at Billion Scale on Douyin, 2025.11,
• HHFT: Hierarchical Heterogeneous Feature Transformer for Recommendation Systems, 2025.11,
• OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender, 2025.10,
• RankMixer: Scaling Up Ranking Models in Industrial Recommenders, 2025.07,
• Scaling Transformers for Discriminative Recommendation via Generative Pretraining, 2025.06,
• LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders, 2025.05,
• Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations, 2024.02,

Cross-Domain

Papers on cross-domain, multi-domain, and multi-scenario recommendation modeling

• A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation, 2025.11,

• Cross-Scenario Unified Modeling of User Interests at Billion Scale, 2025.10,

• Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model, 2025.02,

Diffusion-based

Papers that explore diffusion-based generative paradigms for recommendation

• Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion, 2026.03,
• Masked Diffusion Generative Recommendation, 2026.01,
• MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation, 2025.11,
• DiffGRM: Diffusion-based Generative Recommendation Model, 2025.10,

LLM-based

Papers that leverage LLMs or foundation models for generative recommendation

• OneReason Technical Report, 2026.06,
• SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress, 2026.02,
• OpenOneRec Technical Report, 2025.12,
• OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation, 2025.12,
• RecGPT-V2 Technical Report, 2025.12,
• Align3GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation, 2025.11,
• OneRec-Think: In-Text Reasoning for Generative Recommendation, 2025.10,
• PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations, 2025.10,
• OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System, 2025.09,
• HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation, 2025.08,
• PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform, 2025.07,
• HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling, 2024.09,
• LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application, 2024.05,

One Model

Papers on unified end-to-end generative recommendation frameworks

• OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender, 2026.09,
• UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale, 2026.06,
• OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework, 2026.03,
• Generative Recommendation for Large-Scale Advertising, 2026.02,
• DualGR: Generative Retrieval with Long and Short-Term Interests Modeling, 2025.11,
• GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation, 2025.11,
• SynerGen: Contextualized Generative Recommender for Unified Search and Recommendation, 2025.09,
• OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search, 2025.09,
• OneRec-V2 Technical Report, 2025.08,
• RecGPT Technical Report, 2025.07,
• OneRec Technical Report, 2025.06,
• OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion, 2025.06,
• EGA-V1: Unifying Online Advertising with End-to-End Learning, 2025.05,
• EGA-V2: An End-to-end Generative Framework for Industrial Advertising, 2025.05,
• Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations, 2025.03,
• OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment, 2025.02,

Post Train

Papers on post-training techniques (preference alignment, RLHF, reward modeling) for generative recommendation

• Reward Guided Decoding for Generative Recommendation, 2026.07,

Ranking

Generative Ranking papers

• UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute, 2026.04,
• MTGR: Industrial-Scale Generative Recommendation Framework in Meituan, 2025.05,
• Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation, 2025.05,
• MTGRBoost: Boosting Large-scale Generative Recommendation Models in Meituan, 2025.05,
• Towards Large-scale Generative Ranking, 2025.05,

Retrieval

Generative Retrieval papers

• Multi-Decoder OneRec: Controllable Generative Retrieval for Multi-Objective Industrial Recommendation, 2026.07,
• UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute, 2026.04,
• OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation, 2026.02,
• OneLoc: Geo-Aware Generative Recommender Systems for Local Life Service, 2025.08,
• TBGRecall: A Generative Retrieval Model for E-commerce Recommendation Scenarios, 2025.08,
• Next-User Retrieval: Enhancing Cold-Start Recommendations via Generative Next-User Modeling, 2025.06,
• PinRec: Outcome-Conditioned, Multi-Token Generative Retrieval for Industry-Scale Recommendation Systems, 2025.04,
• Unifying Generative and Dense Retrieval for Sequential Recommendation, 2024.11,
• Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation, 2023.11,
• Recommender Systems with Generative Retrieval, 2023.11,

Semantic ID

Semantic ID papers

• TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems, 2026.06,
• R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation, 2026.04,
• Differentiable Geometric Indexing for End-to-End Generative Retrieval, 2026.03,
• Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale, 2026.03,
• QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling, 2026.02,
• PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendation, 2026.02,
• Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer, 2026.02,
• Farewell to Item IDs: Unlocking the Scaling Potential of Large Ranking Models via Semantic Tokens, 2026.01,
• MERGE: Next-Generation Item Indexing Paradigm for Large-Scale Streaming Recommendation, 2026.01,
• CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation, 2025.11,
• FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets, 2025.09,
• DAS: Dual-Aligned Semantic IDs Empowered Industrial Recommender System, 2025.08,
• Unified Semantic and ID Representation Learning for Deep Recommenders, 2025.02,
• QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou, 2024.11,
• Autoregressive Image Generation using Residual Quantization, 2022.03,
• Neural Discrete Representation Learning, 2017,

👥 Contributors

⭐ Star History