mlsanityData to 14 Oct 2026

Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding

arXiv 2607.28659 ↗First posted 21 Jul 2026cs.AIcited by 0

On the map: Efficient LLM inference and serving → Speculative decoding

Abstract (arXiv)

Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains. Recently, generative recommendation (GR) has emerged. It first learns semantic identifiers (SIDs) from item semantics and formulates recommendation as autoregressive generation. However, existing methods face two critical issues: (1) they ignore collaborative correlations across domains during tokenization, and (2) they adopt inefficient decoding strategies, such as beam search, during generation, which hinders real-time deployment. To address these limitations, we propose GenCDSR, an effective and efficient generative framework for CDSR. Specifically, we design a cross-domain hybrid tokenization mechanism with a multi-tower architecture to jointly capture cross-domain commonalities and domain-specific distinctions through hierarchical shared-specific and fine-grained codebooks. Furthermore, we develop a cross-domain serial-parallel decoding strategy that leverages the hierarchical SID structure to partially parallelize generation, significantly reducing inference latency while preserving generation consistency. Experiments on three public datasets show that GenCDSR achieves an average accuracy improvement of 1.5 percent and an average inference latency reduction of 85.1 percent compared with state-of-the-art baselines. The implementation code and datasets are available online: https://github.com/Applied-Machine-Learning-Lab/RecSys2026_GenCDSR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving. Builds on 42 of its 61 references that are in the map. First posted on arXiv 21 Jul 2026.

Builds on

42 of 61 references.

References · 42

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023Qwen Technical Reportcited by 3,344
  5. 2018Self-Attentive Sequential Recommendationcited by 1,184
  6. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  7. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  8. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  9. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  10. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  11. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  12. 2023Recommender Systems with Generative Retrievalcited by 198
30 more
  1. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
  2. 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
  3. 2024Learnable Item Tokenization for Generative Recommendationcited by 110
  4. 2023GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretationcited by 103
  5. 2018Deep Reinforcement Learning for Page-wise Recommendationscited by 100
  6. 2019DDTCDR: Deep Dual Transfer Cross Domain Recommendationcited by 72
  7. 2018Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learningcited by 71
  8. 2023GenRec: Large Language Model for Generative Recommendationcited by 63
  9. 2023Multimodal Recommender Systems: A Surveycited by 37
  10. 2021Personalized Transfer of User Preferences for Cross-domain Recommendationcited by 34
  11. 2023Contrastive Cross-Domain Sequential Recommendationcited by 31
  12. 2024Rethinking Large Language Model Architectures for Sequential Recommendationscited by 27
  13. 2023Multi-Task Recommendations with Reinforcement Learningcited by 26
  14. 2023AutoMLP: Automated MLP for Sequential Recommendationscited by 25
  15. 2023HAMUR: Hyper Adapter for Multi-Domain Recommendationcited by 21
  16. 2023Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptionscited by 20
  17. 2023Triple Sequence Learning for Cross-domain Recommendationcited by 19
  18. 2023Denoising and Prompt-Tuning for Multi-Behavior Recommendationcited by 18
  19. 2025FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasetscited by 17
  20. 2023A Unified Framework for Multi-Domain CTR Prediction via Large Language Modelscited by 16
  21. 2024A Survey on Cross-Domain Sequential Recommendationcited by 16
  22. 2025Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendationcited by 15
  23. 2024APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generationcited by 12
  24. 2024SIGMA: Selective Gated Mamba for Sequential Recommendationcited by 10
  25. 2025From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenizationcited by 9
  26. 2025TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Frameworkcited by 7
  27. 2025MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognitioncited by 4
  28. 2025Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuningcited by 4
  29. 2025Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selectioncited by 2
  30. 2025LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Trainingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation
  2. 2026Hierarchical Quantization with Domain-Adaptive Sparse Routing for Generative Cross-Domain Recommendation ↗
  3. 2025Generative Multi-Target Cross-Domain Recommendation
  4. 2024Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation
  5. 2025Universal Item Tokenization for Transferable Generative Recommendation
  6. 2025LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation
  7. 2025Semantics Meet Signals: Dual Codebook Representationl Learning for Generative Recommendation
  8. 2025CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation